DeepMoA: method to predict the mechanism of action of cancer drugs

Select data and import libraries

import sys # we require code from other folders
import pandas as pd
import numpy as np
import itertools
import pickle
import os
os.environ['KMP_DUPLICATE_LIB_OK']='True'

import seaborn as sns
import matplotlib.pyplot as plt
CB_color_cycle = ['#EECC16', '#62BB35', '#FDAE33','#208EA3', '#EA4E9D', '#984ea3','#999999', '#e41a1c', '#dede00']
#sns.set_style("darkgrid")

import matplotlib.font_manager as fm
font_files = fm.findSystemFonts()

plt.rcdefaults()
# Go through and add each to Matplotlib's font cache.
for font_file in font_files:
    fm.fontManager.addfont(font_file)
plt.rc('font', family='Roboto')

plt.rc('font', family='Roboto')

plt.rcParams['font.family'] = 'sans-serif'
plt.rcParams['font.sans-serif'] = 'Roboto'

#%config InlineBackend.figure_format='retina'

# pytorch relates imports
import torch
import torch.nn as nn
import torch.optim as optim

# imports from captum library
from captum.attr import LayerDeepLift

# for combobox
from __future__ import print_function
from ipywidgets import interact, interactive, fixed, interact_manual
import ipywidgets as widgets

import plotly.express as px
import plotly.graph_objects as go
import plotly.io as pio

pd.options.display.min_rows = 20000
pd.set_option('max_colwidth', 200)

pd.options.display.max_rows = 20000

pd.set_option('min_rows', 20000)

mac = "/Users/katyna/Library/CloudStorage/OneDrive-Tecnun/"
windows = "C:/Users/ksada/OneDrive - Tecnun/"
computer = windows # CHANGE

sys.path.append(computer + "SparseGO_code/code")
import util
from util import *

%matplotlib inline

#%matplotlib inline

# To make histograms
def histogram(dataframe, color, title, ylabel,n_bins):
    N, bins, patches = plt.hist(dataframe, color=color,bins=n_bins, linewidth=0.1)

    for i in range(0,len(bins)-1):
        if bins[i]<0.05:
            patches[i].set_facecolor(CB_color_cycle[2])

    plt.xlabel("P-value", fontsize=16)  
    plt.ylabel(ylabel, fontsize=16)
    plt.title(title, fontsize=16)
    plt.xticks(fontsize=14)  
    plt.yticks(fontsize=14)
    ax = plt.subplot(111)  
    ax.spines["top"].set_visible(False)  
    ax.spines["right"].set_visible(False)    

inputdir = computer+"SparseGO_code/data/cross_validation_expression/allsamples/" # CHANGE
dir1=computer+"Tesis/Codigo/VariableImportance/"
dir2=computer+"SparseGO_code/results/weights&biases/Expression_MSE_all/" # CHANGE
resultsdir=dir2

gene2id = inputdir+"gene2ind.txt"
cell2id=inputdir+"cell2ind.txt"
drug2id=inputdir+"drug2ind.txt"
drug2fingerprint=inputdir+"drug2fingerprint.txt"
load=resultsdir+"last_model.pt"

onto = inputdir+"ontology.txt"  # CHANGE 
genotype=inputdir+"cell2expression.txt"  # CHANGE 

num_neurons_per_GO = 6 # CHANGE

DeepLIFT

gene2id_mapping = load_mapping(gene2id)
dG, terms_pairs, genes_terms_pairs = load_ontology(onto, gene2id_mapping)
sorted_pairs, level_list, level_number = sort_pairs(genes_terms_pairs, terms_pairs, dG, gene2id_mapping)
layer_connections = pairs_in_layers(sorted_pairs, level_list, level_number) 

cell_features = np.genfromtxt(genotype, delimiter=',')
drug_features = np.genfromtxt(drug2fingerprint, delimiter=',')

drug2id_mapping = load_mapping(drug2id)
cell2id_mapping = load_mapping(cell2id)

num_genes = len(gene2id_mapping)
drug_dim = len(drug_features[0,:])

There are 15015 genes
There are 1 roots: GO:0008150
There are 4184 terms
There are 1 connected components

model = torch.load(load, map_location='cuda:%d' % 0)

model

sparseGO_nn(
  (genes_terms_sparse_linear_1): SparseLinearNew(
    in_features=15015, out_features=25104, bias=True, sparsity=0.0030196221878822263, connectivity=tensor([[    0,     1,     2,  ..., 23721, 23722, 23723],
            [    0,     0,     0,  ..., 15014, 15014, 15014]], device='cuda:0'), small_world=False
  )
  (genes_terms_tanh): Tanh()
  (genes_terms_batchnorm): BatchNorm1d(25104, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (GO_terms_sparse_linear_1): SparseLinearNew(
    in_features=25104, out_features=8304, bias=True, sparsity=0.002372788160788691, connectivity=tensor([[  966,   967,   968,  ...,  7047,  7048,  7049],
            [    0,     0,     0,  ..., 25103, 25103, 25103]], device='cuda:0'), small_world=False
  )
  (GO_terms_tanh_1): Tanh()
  (GO_terms_batchnorm_1): BatchNorm1d(8304, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (GO_terms_sparse_linear_2): SparseLinearNew(
    in_features=8304, out_features=3684, bias=True, sparsity=0.003911619061964564, connectivity=tensor([[   0,    1,    2,  ..., 3681, 3682, 3683],
            [   0,    0,    0,  ..., 8303, 8303, 8303]], device='cuda:0'), small_world=False
  )
  (GO_terms_tanh_2): Tanh()
  (GO_terms_batchnorm_2): BatchNorm1d(3684, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (GO_terms_sparse_linear_3): SparseLinearNew(
    in_features=3684, out_features=1650, bias=True, sparsity=0.007924193070772875, connectivity=tensor([[ 150,  151,  152,  ..., 1641, 1642, 1643],
            [   0,    0,    0,  ..., 3683, 3683, 3683]], device='cuda:0'), small_world=False
  )
  (GO_terms_tanh_3): Tanh()
  (GO_terms_batchnorm_3): BatchNorm1d(1650, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (GO_terms_sparse_linear_4): SparseLinearNew(
    in_features=1650, out_features=726, bias=True, sparsity=0.015807663410969196, connectivity=tensor([[ 474,  475,  476,  ...,  711,  712,  713],
            [   0,    0,    0,  ..., 1649, 1649, 1649]], device='cuda:0'), small_world=False
  )
  (GO_terms_tanh_4): Tanh()
  (GO_terms_batchnorm_4): BatchNorm1d(726, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (GO_terms_sparse_linear_5): SparseLinearNew(
    in_features=726, out_features=318, bias=True, sparsity=0.03305785123966942, connectivity=tensor([[ 60,  61,  62,  ..., 105, 106, 107],
            [  0,   0,   0,  ..., 725, 725, 725]], device='cuda:0'), small_world=False
  )
  (GO_terms_tanh_5): Tanh()
  (GO_terms_batchnorm_5): BatchNorm1d(318, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (GO_terms_sparse_linear_6): SparseLinearNew(
    in_features=318, out_features=120, bias=True, sparsity=0.06981132075471698, connectivity=tensor([[  0,   1,   2,  ...,  93,  94,  95],
            [  0,   0,   0,  ..., 317, 317, 317]], device='cuda:0'), small_world=False
  )
  (GO_terms_tanh_6): Tanh()
  (GO_terms_batchnorm_6): BatchNorm1d(120, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (GO_terms_sparse_linear_7): SparseLinearNew(
    in_features=120, out_features=42, bias=True, sparsity=0.2, connectivity=tensor([[ 18,  19,  20,  ...,  21,  22,  23],
            [  0,   0,   0,  ..., 119, 119, 119]], device='cuda:0'), small_world=False
  )
  (GO_terms_tanh_7): Tanh()
  (GO_terms_batchnorm_7): BatchNorm1d(42, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (GO_terms_sparse_linear_8): SparseLinearNew(
    in_features=42, out_features=30, bias=True, sparsity=1.0, connectivity=tensor([[ 0,  1,  2,  ..., 27, 28, 29],
            [ 0,  0,  0,  ..., 41, 41, 41]], device='cuda:0'), small_world=False
  )
  (GO_terms_tanh_8): Tanh()
  (GO_terms_batchnorm_8): BatchNorm1d(30, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (drug_linear_layer_1): Linear(in_features=2048, out_features=200, bias=True)
  (drug_tanh_1): Tanh()
  (drug_batchnorm_layer_1): BatchNorm1d(200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (drug_linear_layer_2): Linear(in_features=200, out_features=100, bias=True)
  (drug_tanh_2): Tanh()
  (drug_batchnorm_layer_2): BatchNorm1d(100, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (drug_linear_layer_3): Linear(in_features=100, out_features=50, bias=True)
  (drug_tanh_3): Tanh()
  (drug_batchnorm_layer_3): BatchNorm1d(50, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (final_linear_layer): Linear(in_features=80, out_features=40, bias=True)
  (final_tanh): Tanh()
  (final_batchnorm_layer): BatchNorm1d(40, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (final_aux_linear_layer): Linear(in_features=40, out_features=1, bias=True)
  (final_aux_tanh): Tanh()
  (final_linear_layer_output): Linear(in_features=1, out_features=1, bias=True)
)

# Save layers to be analyzed
model_layers = []
model_layers.append(model.genes_terms_sparse_linear_1)
model_layers.append(model.GO_terms_sparse_linear_1)
model_layers.append(model.GO_terms_sparse_linear_2)
model_layers.append(model.GO_terms_sparse_linear_3)
model_layers.append(model.GO_terms_sparse_linear_4)
model_layers.append(model.GO_terms_sparse_linear_5)
model_layers.append(model.GO_terms_sparse_linear_6)
model_layers.append(model.GO_terms_sparse_linear_7)

GO terms info

# Go term names
gene_ontology = pd.read_excel('all_go_terms_info.xlsx')

Get all layers’ GO term with the neuron number

all_terms_ids = {}
all_terms_names = {}
all_layers_non_virtual = {} # store only terms that are part of the layer (remove virtual), those are the important attribuitions
all_layers_non_virtual_names = {}
num_neurons_per_GO = 6

for layer_number in range(len(layer_connections)-1):
    layer_pairs = layer_connections[layer_number] 
    
    terms_ids = []
    names = []
    output_id = create_index(layer_pairs[:,0]) # first 6 neurons correspond to the term with key 0
    
    for term in output_id.keys():
        #name = gene_ontology.loc[gene_ontology['GO_term'] == term].to_numpy()[0,3].replace("_"," ").capitalize()
        name = gene_ontology.loc[gene_ontology['id'] == term].to_numpy()[0,1].capitalize()
        for i in range(1,num_neurons_per_GO+1): # vector que tiene GO:0000038_1, GO:0000038_2 ... GO:0000038_6 y asi luego concatenar con las attributions
            terms_ids.append(term+"_"+str(i))
            names.append(name+" ("+str(i)+")")
    all_terms_ids[layer_number] = np.array(terms_ids)
    all_terms_names[layer_number] = np.array(names)

    non_virtual = [] # store the terms part of that layer
    non_virtual_names = []
    for term in level_list[layer_number+1]:
        nv_name = gene_ontology.loc[gene_ontology['id'] == term].to_numpy()[0,1].capitalize()
        for i in range(1,7):
            non_virtual.append(term+"_"+str(i))
            non_virtual_names.append(nv_name+" ("+str(i)+")")
    all_layers_non_virtual[layer_number] = non_virtual
    all_layers_non_virtual_names[layer_number] = non_virtual_names

All GO terms part of a layer (non-virtual) with their corresponding name and layer number…

real_go_info = pd.DataFrame({"GO_term":[],"Name":[],"layer_number":[]})
for layer_number in range(len(layer_connections)-1):
    layer_go_info = pd.DataFrame({"GO_term":all_layers_non_virtual[layer_number],"Name":all_layers_non_virtual_names[layer_number],"layer_number":(layer_number)})
    real_go_info = pd.concat((real_go_info,layer_go_info))
real_go_info.head()

	GO_term	Name	layer_number
0	GO:0000019_1	Regulation of mitotic recombination (1)	0.0
1	GO:0000019_2	Regulation of mitotic recombination (2)	0.0
2	GO:0000019_3	Regulation of mitotic recombination (3)	0.0
3	GO:0000019_4	Regulation of mitotic recombination (4)	0.0
4	GO:0000019_5	Regulation of mitotic recombination (5)	0.0

Drugs info

def get_compound_names(file_name):
    compounds = []

    with open(file_name, 'r') as fi:
        for line in fi:
            tokens = line.strip().split('\t')
            compounds.append([tokens[1],tokens[2]])
    return compounds

drugs = get_compound_names(inputdir+"compound_names.txt")
drugs.pop(0)

['SMILE', 'Name']

DeepLIFT for VNN

Reference activation… (baseline)

median_cell_features = np.median(cell_features,axis=0) # to use as a reference
median_drug_features = np.genfromtxt(computer+"SparseGO_code/data/glucose_fingerprint.txt", delimiter=',')

Attribution function: sum

def get_layer_attribution(layer_number,input_data,baseline,selected_drug_data):
    dl = LayerDeepLift(model, model_layers[layer_number],multiply_by_inputs = True) # CHOOSE LAYER TO STUDY
    dl_attr_test = dl.attribute(input_data,baseline)
    dl_attr_test_sum = dl_attr_test.cpu().detach().numpy().sum(0) # se suman las attributions para cada sample
    
    attribution_data = pd.DataFrame(np.column_stack((all_terms_ids[layer_number],dl_attr_test_sum)), columns=["GO_term",selected_drug_data[1]])
    attribution_data[[selected_drug_data[1]]] = attribution_data[[selected_drug_data[1]]].apply(pd.to_numeric).round(10)
    attribution_data = attribution_data.loc[attribution_data['GO_term'].isin(all_layers_non_virtual[layer_number])] # only the keep the non virtual terms
    return attribution_data

DeepLIFT for all drugs

attribution_data_all = pd.DataFrame()
# Obtain the top GO terms on all layers for each drug
for selected_drug_data in drugs:
    selected_drug =selected_drug_data[0] # DRUG smile
    selected_drug_features = []
    drug_specific_features=drug_features[drug2id_mapping[selected_drug]] # features of drug
    
    for i in range(len(cell2id_mapping)): # make all combinations of selected_drug and cell types 
        selected_drug_features.append(np.concatenate((cell_features[i], drug_specific_features), axis=None))
    selected_drug_features = torch.FloatTensor(np.array(selected_drug_features))

    # Data for deeplift...
    input_data = torch.autograd.Variable(selected_drug_features.cuda(0))
    
    #median_drug_features = drug_specific_features
    # baseline is the median of the expression data and drug features 
    baseline = torch.FloatTensor(np.concatenate((median_cell_features, median_drug_features), axis=None))
    baseline = torch.reshape(baseline, (1, baseline.size()[0]))
    baseline = torch.autograd.Variable(baseline.cuda(0))
    
    attribution_data_drug = list(map(get_layer_attribution,range(0,len(model_layers)),itertools.repeat(input_data, len(model_layers)),itertools.repeat(baseline, len(model_layers)),itertools.repeat(selected_drug_data, len(model_layers)))) # get the attribution for each layer (map is similar to apply)
    attribution_data_drug = pd.concat(attribution_data_drug) # concatenate attribution of all layers
    
    attribution_data_all = pd.concat([attribution_data_all,attribution_data_drug.iloc[:,1]], axis=1)
    
    print(selected_drug_data[1])
    
attribution_data_all = pd.concat([attribution_data_drug.iloc[:,0],attribution_data_all], axis=1)

attribution_data_all = attribution_data_all.set_index("GO_term")

attribution_data_all.head()

	BRD-K02251932-001-01-3	BRD-K25737009-001-01-2	Nintedanib	bicalutamide	N-[(2R,3S)-2-[[cyclopropylmethyl(methyl)amino]methyl]-5-[(2R)-1-hydroxypropan-2-yl]-3-methyl-6-oxo-3,4-dihydro-2H-1,5-benzoxazocin-8-yl]-1-methyl-4-imidazolesulfonamide	PHA-665752	N-cyclopropyl-3-[3-[[cyclopropyl(oxo)methyl]amino]-1H-indazol-6-yl]benzamide	Ki8751	IPA-3	FAWUGYGEBHAQBU-PPEXNQRJSA-N	...	ML031	Semagacestat	RITA	CDK9 inhibitor	Dasatinib	BMS-536924;CC1=CC(=CC2=C1NC(=C3C(=CC=NC3=O)NC[C@H](C4=CC(=CC=C4)Cl)O)N2)N5CCOCC5	SCHEMBL13741284	Daporinad	STF-31	Narciclasine
GO_term
GO:0000012_1	-0.006564	-0.005680	0.003188	-0.005863	-0.003410	-0.002951	0.001118	0.002033	0.000799	-0.007842	...	-0.007256	-0.004271	-0.013783	-0.006253	0.002864	0.009604	-0.008099	-0.001475	-0.003698	-0.009866
GO:0000012_2	0.010029	0.011514	0.009892	0.012072	0.005788	0.012909	0.002316	0.009362	-0.011816	0.000166	...	0.008918	-0.002449	0.017704	0.006732	0.002447	0.006485	0.003888	-0.000569	0.001628	0.017132
GO:0000012_3	0.008466	0.006840	-0.000027	0.006379	0.003082	-0.006110	-0.008877	-0.000347	-0.013084	0.000150	...	-0.006096	0.011308	0.012216	0.000997	0.011521	0.013800	0.002843	0.016328	0.021640	0.003536
GO:0000012_4	0.013018	0.007276	0.010128	0.008622	0.004795	0.006706	0.000874	0.005514	-0.003347	-0.000010	...	-0.003682	0.006544	0.010806	0.003346	0.017556	0.023130	0.001105	0.009710	0.016940	0.014787
GO:0000012_5	-0.007076	-0.006129	-0.007634	-0.003785	-0.004151	-0.007947	-0.008430	-0.006039	-0.002722	0.002163	...	0.001821	-0.002346	-0.007831	-0.009368	-0.011118	-0.003408	-0.001760	0.003593	-0.000109	-0.020831

5 rows × 684 columns

ChEMBL Drug Target Slim

from chembl_webresource_client.new_client import new_client

Import SparseGO drugs

# Get names 
def get_compound_names(file_name):
    compounds = []

    with open(file_name, 'r') as fi:
        for line in fi:
            tokens = line.strip().split('\t')
            compounds.append(tokens[2].lower())

    return compounds
names = get_compound_names(computer+"SparseGO_code/data/compound_names.txt")
names.pop(0)

'name'

chEML IDs

Get chembl IDs of drugs if available (there are always 684 drugs, the compounds2ids object can be reused)

# Get all chembl IDs -- tarda
molecule = new_client.molecule

compounds2ids = {}
for i,drug in enumerate(names):
    
    if " + " in drug:
        drug_split = drug.split(" + ", 1)
        ID1 = list(molecule.filter(pref_name__iexact=drug_split[0]).only('molecule_chembl_id'))
        ID2 = list(molecule.filter(pref_name__iexact=drug_split[1]).only('molecule_chembl_id'))
        if len(ID1)>0 and len(ID2)>0:
            compounds2ids[drug]=[ID1[0]['molecule_chembl_id'],ID2[0]['molecule_chembl_id']]
        elif len(ID1)>0:
            compounds2ids[drug]=ID1[0]['molecule_chembl_id'] 
        elif len(ID2)>0:
            compounds2ids[drug]=ID2[0]['molecule_chembl_id'] 
        else:
            print(drug,i)

    else:
        ID = list(molecule.filter(pref_name__iexact=drug).only('molecule_chembl_id'))
        if len(ID)>0:
            ID = ID[0]['molecule_chembl_id']
            compounds2ids[drug]=ID
        else:
            # for drugs that have the chembl ID as the name!!
            ID = list(molecule.filter(chembl_id=drug).only('molecule_chembl_id')) 
            if len(ID)>0:
                ID = ID[0]['molecule_chembl_id']
                compounds2ids[drug]=ID
            else:
                # in case it is not found by pref_name
                ID = list(molecule.filter(molecule_synonyms__molecule_synonym__iexact=drug).only('molecule_chembl_id'))
                if len(ID)>0:
                    ID = ID[0]['molecule_chembl_id']
                    compounds2ids[drug]=ID
                else:
                    print(drug,i)
    # 341 chembl IDs where found (october 31 2022)

#manually add 6 more
compounds2ids["teniposide [usan]"]="CHEMBL452231"
compounds2ids["docetaxel (taxotere)"]="CHEMBL92"
compounds2ids["nan + navitoclax(1)"]="CHEMBL443684"
compounds2ids["nan + navitoclax(2)"]="CHEMBL443684"
compounds2ids["osi-027;coc1=cc=cc2=cc(=c3c4=c(n=cnn4c(=n3)c5ccc(cc5)c(=o)o)n)n=c21"]="CHEMBL3120215"
compounds2ids["paclitaxel;cc1=c2[c@h](c(=o)[c@@]3([c@h](c[c@@h]4[c@]([c@h]3[c@@h]([c@@](c2(c)c)(c[c@@h]1oc(=o)[c@@h]([c@h](c5=cc=cc=c5)nc(=o)c6=cc=cc=c6)o)o)oc(=o)c7=cc=cc=c7)(co4)oc(=o)c)o)c)oc(=o)c"]="CHEMBL428647"

len(compounds2ids)

347

chEMBL MoA (targets)

Get the molecule targets of each drug (if available)

compounds2targets = dict() # required to store the drug targets 
for drug in compounds2ids.keys():
    compounds2targets[drug] = set()

chembl_ids = list(compounds2ids.values()) # Chembl IDs of drugs

for drug in compounds2ids:
    # we jump from compounds to targets through activities:
    activities = new_client.mechanism.filter(parent_molecule_chembl_id__in=compounds2ids[drug]).only(
        ['parent_molecule_chembl_id', 'target_chembl_id'])
    # extracting target ChEMBL IDs from activities:
    for act in activities:
        compounds2targets[drug].add(act['target_chembl_id'])
    print(drug)
# We now know all targets for some drug

compounds2targets = {k: v for k, v in compounds2targets.items() if len(v) != 0 and len([x for x in list(v) if x is not None]) != 0 }
# 218 DRUGS HAVE ANNOTATED DRUG TARGETS

len(compounds2targets)

220

Drug slim GO terms

Get the GO terms of each target

# Get the GO terms of each target
compounds_GOterms = {}
for i in range(0, len(compounds2targets.keys())):
    compound = list(compounds2targets.keys())[i]
    GOterms_list = []
    
    for j in range(0, len(list(compounds2targets[compound]))):   
        target = list(compounds2targets[compound])[j]
        all_cross_references = list(new_client.target.filter(target_chembl_id=target).only(['target_components']).only(['target_components_xrefs']))[0]['target_components']
        if len(all_cross_references)>0: # not all targets have annotated go_terms
            for i in range(0, len(all_cross_references)):
                GOterms = all_cross_references[i]
                GOterms = pd.DataFrame(GOterms['target_component_xrefs'])
                GOterms = pd.concat([GOterms,pd.Series([target]).repeat(len(GOterms)).reset_index().pop(0)],axis=1) # add target ID to dataframe 
                GOterms_list= GOterms_list + GOterms.values.tolist()
    
    compounds_GOterms[compound] =  pd.DataFrame(GOterms_list).drop_duplicates()
    print(compound)

len(compounds_GOterms)

220

# we have 206 annotated drugs on CHEMBL

# add GO terms found in CTRPv2

CTRPv2_terms = pd.read_excel('ctrp_goterms_drugs.xlsx')  

# add GO terms of drugs with or without annotations
for drug in CTRPv2_terms["Drug"].unique():
    if drug not in list(compounds_GOterms.keys()): # some drugs had no previous data, no annotations from chembl
        compounds_GOterms[drug] = pd.DataFrame() # create empty dataframe

    for term in list(CTRPv2_terms.loc[CTRPv2_terms["Drug"]==drug]["Field"]):
        compounds_GOterms[drug] = pd.concat([compounds_GOterms[drug],pd.DataFrame([term,"","GoProcess",""]).transpose()])
    compounds_GOterms[drug] = compounds_GOterms[drug].drop_duplicates() 

# now we have 233 annotated drugs

# Delete drugs with no GOterms (some targets have no annotated GO terms)
compounds_GOterms = {k: v for k, v in compounds_GOterms.items() if len(v) != 0 } 

len(compounds_GOterms)

236

Match GO terms

Find all terms that match, terms that are part of both, the sparseGO graph and the drug slim results…

def load_ontology_extra_output(ontology_file, gene2id_mapping):
    """
    Creates the directed graph of the GO terms and stores the connected elements in arrays.

        Output
        ------
        dG: networkx.classes.digraph.DiGraph
            Directed graph of all terms

        terms_pairs: numpy.ndarray
            Store the connection between a term and a term

        genes_terms_pairs: numpy.ndarray
            Store the connection between a gene and a term
    """

    dG = nx.DiGraph() # Directed graph class

    file_handle = open(ontology_file) #  Open the file that has genes and go terms

    terms_pairs = [] # store the pairs between a term and a term
    genes_terms_pairs = [] # store the pairs between a gene and a term

    gene_set = set() # create a set (elements can't repeat)
    term_direct_gene_map = {}
    term_size_map = {}


    for line in file_handle:

        line = line.rstrip().split() # delete spaces and transform to list, line has 3 elements

        # No me hace falta el if, no tengo que separar las parejas
        if line[2] == 'default': # si el tercer elemento es default entonces se conectan los terms en el grafo
            dG.add_edge(line[0], line[1]) # Add an edge between line[0] and line[1]
            terms_pairs.append([line[0], line[1]]) # Add the pair to the list
        else:
            if line[1] not in gene2id_mapping: # se salta el gen si no es parte de los que estan en gene2id_mapping
                print(line[1])
                continue

            genes_terms_pairs.append([line[0], line[1]]) # add the pair

            if line[0] not in term_direct_gene_map: # si el termino todavia no esta en el diccionario lo agrega
                term_direct_gene_map[ line[0] ] = set() # crea un set

            term_direct_gene_map[line[0]].add(gene2id_mapping[line[1]]) # añadimos el gen al set de ese term

            gene_set.add(line[1]) # añadimos el gen al set total de genes

    terms_pairs = np.array(terms_pairs) # convert to 2d array
    genes_terms_pairs = np.array(genes_terms_pairs) # convert to 2d array

    file_handle.close()

    print('There are', len(gene_set), 'genes')

    for term in dG.nodes(): # hacemos esto para cada uno de los GO terms

        term_gene_set = set() # se crea un set

        if term in term_direct_gene_map:
            term_gene_set = term_direct_gene_map[term] # genes conectados al term

        deslist = nxadag.descendants(dG, term) #regresa todos sus GO terms descendientes (biological processes tiene 2085 descendientes, todos menos el mismo)

        for child in deslist:
            if child in term_direct_gene_map: # añadir los genes de sus descendientes
                term_gene_set = term_gene_set | term_direct_gene_map[child] # union of both sets, ahora tiene todos los genes los suyos y los de sus descendientes

        if len(term_gene_set) == 0:
            print('There is empty terms, please delete term:', term)
            sys.exit(1)
        else:
            # por ahora esta variable no me hace falta
            term_size_map[term] = len(term_gene_set) # cantidad de genes en ese term  (tomando en cuenta sus descendientes)

    leaves = [n for n in dG.nodes if dG.in_degree(n) == 0] # buscar la raiz
    #leaves = [n for n,d in dG.in_degree() if d==0]

    uG = dG.to_undirected() # Returns an undirected representation of the digraph
    connected_subG_list = list(nxacc.connected_components(uG)) #list of all GO terms

    # Verify my graph makes sense...
    print('There are', len(leaves), 'roots:', leaves[0])
    print('There are', len(dG.nodes()), 'terms')
    print('There are', len(connected_subG_list), 'connected components')
    if len(leaves) > 1:
        print('There are more than 1 root of ontology. Please use only one root.')
        sys.exit(1)
    if len(connected_subG_list) > 1:
        print( 'There are more than connected components. Please connect them.')
        sys.exit(1)

    return dG, terms_pairs, genes_terms_pairs, term_direct_gene_map, term_size_map

SparseGO graph

# Import SparseGO graph (to extract all nodes/terms)... 

# Load ontology: create the graph of connected GO terms
dG, terms_pairs, genes_terms_pairs, term_direct_gene_map, term_size_map = load_ontology_extra_output(onto, gene2id_mapping)
####
sparseGO_terms = list(dG.nodes())
sparseGO_terms.remove("GO:0008150")

There are 15015 genes
There are 1 roots: GO:0008150
There are 4184 terms
There are 1 connected components

Full GO graph

# Import full graph (to find parents)...
import obonet
#import networkx as nx
url = 'http://purl.obolibrary.org/obo/go/go-basic.obo'
full_graph = obonet.read_obo(url)
full_graph = full_graph.reverse() # change the direction of nodes
[n for n in full_graph.nodes if full_graph.in_degree(n) == 0] # graph contains the 3 roots (BP,MF,CC)

['GO:0003674', 'GO:0005575', 'GO:0008150']

Match terms!

Find all terms that match, terms that are part of both, the sparseGO graph and the drug slim results… if the slim terms’ ascendants are a match, they are also added

# Each model has DIFFERENT matches (the graph is different)
compounds_GOterms_matches = {}
for drug in compounds_GOterms.keys():
    # choose drug
    drug_df = compounds_GOterms[drug]
    drug_slim_GOterms = set(drug_df.loc[drug_df[2] == "GoProcess"][0]) # only GO processes
    #set(sparseGO_terms) & set(drug_slim_GOterms)
    drug_matches = [] # store all directly matched terms and matches with all parents
    for term in drug_slim_GOterms: # term ='GO:1902669' # buen ejemplo 
        
        if term in sparseGO_terms: # is the term in the sparseGO terms? 
            drug_matches.append([1,term]) # add to list
            #1: same term, 2:not direct match  (esto igual despues...the number indicates how direct is the relationship 0:same term, 1: parent, 2: grandpa, 3:...)
        
        # are its ascendants in the sparseGO terms? 
        parents = [source for source, _ in  full_graph.in_edges(term)] # parents of term
        relationship = 2
        while(len(parents)>0): # check all ascendants 
            #relationship+=1
            parents = [source for source, _ in  full_graph.in_edges(parents)] # parents of parents
        
            for parent_term in parents: # add parents that match sparseGO terms 
                if parent_term in sparseGO_terms:
                    drug_matches.append([relationship, parent_term])
        
        drug_matches = (pd.DataFrame(drug_matches).drop_duplicates()).values.tolist() # remove duplicates
        compounds_GOterms_matches[drug] = drug_matches
    print(drug)

# delete drugs that have no matches
compounds_GOterms_matches = {i:j for i,j in compounds_GOterms_matches.items() if j != []}

len(compounds_GOterms_matches)

230

SparseGO terms x drugSlim terms matrix

attribution_data_all.columns = attribution_data_all.columns.str.lower() # in order to match the term

attribution_data_all.head()

	brd-k02251932-001-01-3	brd-k25737009-001-01-2	nintedanib	bicalutamide	n-[(2r,3s)-2-[[cyclopropylmethyl(methyl)amino]methyl]-5-[(2r)-1-hydroxypropan-2-yl]-3-methyl-6-oxo-3,4-dihydro-2h-1,5-benzoxazocin-8-yl]-1-methyl-4-imidazolesulfonamide	pha-665752	n-cyclopropyl-3-[3-[[cyclopropyl(oxo)methyl]amino]-1h-indazol-6-yl]benzamide	ki8751	ipa-3	fawugygebhaqbu-ppexnqrjsa-n	...	ml031	semagacestat	rita	cdk9 inhibitor	dasatinib	bms-536924;cc1=cc(=cc2=c1nc(=c3c(=cc=nc3=o)nc[c@h](c4=cc(=cc=c4)cl)o)n2)n5ccocc5	schembl13741284	daporinad	stf-31	narciclasine
GO_term
GO:0000012_1	-0.006564	-0.005680	0.003188	-0.005863	-0.003410	-0.002951	0.001118	0.002033	0.000799	-0.007842	...	-0.007256	-0.004271	-0.013783	-0.006253	0.002864	0.009604	-0.008099	-0.001475	-0.003698	-0.009866
GO:0000012_2	0.010029	0.011514	0.009892	0.012072	0.005788	0.012909	0.002316	0.009362	-0.011816	0.000166	...	0.008918	-0.002449	0.017704	0.006732	0.002447	0.006485	0.003888	-0.000569	0.001628	0.017132
GO:0000012_3	0.008466	0.006840	-0.000027	0.006379	0.003082	-0.006110	-0.008877	-0.000347	-0.013084	0.000150	...	-0.006096	0.011308	0.012216	0.000997	0.011521	0.013800	0.002843	0.016328	0.021640	0.003536
GO:0000012_4	0.013018	0.007276	0.010128	0.008622	0.004795	0.006706	0.000874	0.005514	-0.003347	-0.000010	...	-0.003682	0.006544	0.010806	0.003346	0.017556	0.023130	0.001105	0.009710	0.016940	0.014787
GO:0000012_5	-0.007076	-0.006129	-0.007634	-0.003785	-0.004151	-0.007947	-0.008430	-0.006039	-0.002722	0.002163	...	0.001821	-0.002346	-0.007831	-0.009368	-0.011118	-0.003408	-0.001760	0.003593	-0.000109	-0.020831

5 rows × 684 columns

attribution_data_all.shape

(25098, 684)

Only keep drugs that have annotated GO terms

attribution_data_annotated = attribution_data_all[list(compounds_GOterms_matches.keys())]

attribution_data_annotated.shape # 230 DRUGS

(25098, 230)

Build drugSlim (MoA) matrix

slim_matrix = attribution_data_annotated.copy() # copy dataframe in order to build a similar matrix 
for col in slim_matrix.columns:
    slim_matrix[col].values[:] = 0 # empty matrix 

for drug in compounds_GOterms_matches.keys():
    drug_matches = compounds_GOterms_matches[drug]
    drug_matches_names = list(pd.DataFrame(drug_matches)[1])
    
    drug_matches_names_duplicated = []
    for term in set(drug_matches_names):
        for i in range(1,7):
            drug_matches_names_duplicated.append(term+"_"+str(i))
    
    slim_matrix[drug][drug_matches_names_duplicated] = 1 # add a 1 if term is annotated to drug

Build matrices to store logits, predictions and real values

logits_matrix = pd.DataFrame(0, index=sparseGO_terms, columns=slim_matrix.columns)
preds_matrix = pd.DataFrame(0, index=sparseGO_terms, columns=slim_matrix.columns)
slim_matrix_single_neuron = pd.DataFrame(0, index=sparseGO_terms, columns=slim_matrix.columns)

Create models

Regression models…

# Dictionaries to store results
GO_terms_auc_log = {}
GO_terms_aupr_log = {}
GO_terms_precision_log = {}

# Perform logistic
for goterm in sparseGO_terms:
    #store results of each cross validation
    # if (real_go_info[real_go_info["GO_term"]==goterm+"_1"]["layer_number"]).values >3:
    #     continue
    
    all_y_test = []
    all_y_pred_proba = []
    all_y_pred = []
    all_y_names = []
    X = []

    goterm_drugs = slim_matrix.loc[[goterm+"_"+str(1)]].values.flatten()

    if sum(goterm_drugs) <= 8:
            continue

    list_nodes = []
    for i in range(1,7):
        list_nodes.append(goterm+"_"+str(i))

    score = attribution_data_annotated.loc[list_nodes].T
    #score_mod = score
    score_mod = score.divide(score.std()).fillna(0) # AFECTA MUCHO

    # Separate drugs in 4 groups for cross-validation -----

    # Split data in 2 groups (with train_test_split in order to have 0s in both groups)
    X_part1,X_part2,y_part1,y_part2=train_test_split(score_mod,goterm_drugs,test_size=0.50,random_state=0,stratify=goterm_drugs)
    # Split data again in 4 groups (split data previously split)
    X_group1,X_group2,y_group1,y_group2=train_test_split(X_part1,y_part1,test_size=0.50,random_state=0,stratify=y_part1)
    X_group3,X_group4,y_group3,y_group4=train_test_split(X_part2,y_part2,test_size=0.50,random_state=0,stratify=y_part2)

    for i in  range(1,5):
        vector = range(0,5)
        group_number = str(i)
        X_test = globals()["X_group"+group_number]
        y_test = globals()["y_group"+group_number]

        # Use the other 3 groups for training 
        keep = list({1,2,3,4}-{int(group_number)}) # remove group number of current test 
        X_train = pd.concat((globals()["X_group"+str(keep[0])],globals()["X_group"+str(keep[1])],globals()["X_group"+str(keep[2])]))
        y_train = np.concatenate((globals()["y_group"+str(keep[0])],globals()["y_group"+str(keep[1])],globals()["y_group"+str(keep[2])]))
        
        logreg = LogisticRegression(penalty="l2",solver="liblinear",max_iter=2000, C=10e-2,class_weight="balanced")
        
        # fit the model with data
        logreg.fit(X_train,y_train)
        y_pred=logreg.predict(X_test)
        y_pred_proba = logreg.predict_proba(X_test)[::,1] # logits for 1 cross-validation
        #y_pred_proba = logreg.decision_function(X_test) # signed distance of sample from hyperplane of your model.
        
        all_y_test.append(y_test)
        all_y_pred_proba.append(y_pred_proba)
        all_y_pred.append(y_pred)
        all_y_names.append(X_test.index)

    all_y_test = np.concatenate(all_y_test)
    all_y_pred_proba = np.concatenate(all_y_pred_proba)
    all_y_names = np.concatenate(all_y_names)
    all_y_pred = np.concatenate(all_y_pred)

    logits_matrix.loc[goterm,all_y_names] = all_y_pred_proba
    slim_matrix_single_neuron.loc[goterm,all_y_names] = all_y_test
    preds_matrix.loc[goterm,all_y_names] = all_y_pred

    # fpr, tpr, _ = metrics.roc_curve(all_y_test,  all_y_pred_proba)
    # GO_terms_auc_log[goterm] = metrics.auc(fpr, tpr) # same as roc_auc_score
    GO_terms_auc_log[goterm] = metrics.roc_auc_score(all_y_test, all_y_pred_proba)

    precision, recall, thresholds = metrics.precision_recall_curve(all_y_test, all_y_pred_proba)
    GO_terms_aupr_log[goterm] = metrics.auc(recall, precision)
    GO_terms_precision_log[goterm] = metrics.precision_score(all_y_test, all_y_pred)

NameError: name 'train_test_split' is not defined

• class_weight=“balanced”… mode uses the values of y to automatically adjust weights inversely proportional to class frequencies in the input data as n_samples / (n_classes * np.bincount(y))

• C , default=1.0… Inverse of regularization strength; must be a positive float. Like in support vector machines, smaller values specify stronger regularization.

• solver{‘newton-cg’, ‘lbfgs’, ‘liblinear’, ‘sag’, ‘saga’}

• Los resultados son iguales si uso predict_proba o decision_function, solo a la hora de interpretar predicted_proba si me da un porcentaje y decision_function una distancia a la recta, el AUC me sale exactamente igual en la regresion logistica

GO_terms_auc_log_df = pd.DataFrame(list(GO_terms_auc_log.items()),columns = ['goterm','auc']).set_index("goterm")
GO_terms_auc_log_df = GO_terms_auc_log_df.dropna()
GO_terms_auc_log_df.sort_values(by=["auc"], ascending=False)

print("There are " +str(len(GO_terms_auc_log_df))+ " logistic regression models.")

# only keep goterms that have a model 
logits_matrix = logits_matrix.loc[list(GO_terms_auc_log_df.index),:]
slim_matrix_single_neuron  = slim_matrix_single_neuron.loc[list(GO_terms_auc_log_df.index),:]
preds_matrix  = preds_matrix.loc[list(GO_terms_auc_log_df.index),:]

AUC histogram

sns.set(rc={'figure.figsize':(10,6)})
fig, ax = plt.subplots()
perc = str(round((100*len(GO_terms_auc_log_df[GO_terms_auc_log_df["auc"]>0.69])/len(GO_terms_auc_log_df)),2))+"%"
N, bins, patches = plt.hist(GO_terms_auc_log_df, color=CB_color_cycle[6],bins=50, linewidth=0.1)

for i in range(0,len(bins)-1):
    if bins[i]>0.69:
        patches[i].set_facecolor(CB_color_cycle[2])

plt.yticks(fontsize=16)
plt.xticks(fontsize=16)

ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)
ax.spines['left'].set_visible(False)
ax.spines['bottom'].set_color('#DDDDDD')

# Second, remove the ticks as well.
ax.tick_params(bottom=False, left=True)

# Third, add a horizontal grid (but keep the vertical grid hidden).
# Color the lines a light gray as well.
ax.set_axisbelow(True)
ax.yaxis.grid(True, color='#EEEEEE')
ax.xaxis.grid(False)

plt.xlabel("AUC value", fontsize=20)
plt.ylabel("Number of GO term models", fontsize=20)
colors2 = {'GO term models with AUC>=0.7':CB_color_cycle[2]}  
labels = list(colors2.keys())
handles = [plt.Rectangle((0,0),1,1, color=colors2[label]) for label in labels]
plt.legend(handles, labels,fontsize=20, loc="lower left", bbox_to_anchor=(0.35,-0.35))
plt.text(0.71, 8, str(perc), fontsize=20,color='#333333')
plt.title("Overall performance of the models using expression", fontsize=24)
# con el que mejor funciona es con la suma normal del attribution 
fig.tight_layout()
fig.savefig(resultsdir+'modelsAUClog.png', transparent=True)

AUC boxplot by parents

# Add number of parents
number_parents = {}
levels = {}
for i in range(0,len(GO_terms_auc_log_df.index)):
    term = GO_terms_auc_log_df.index[i]
    number_parents[GO_terms_auc_log_df.index[i]]=len([source for source, _ in  dG.in_edges(term)])
    levels[GO_terms_auc_log_df.index[i]]=level_number[term]-1
levels = pd.DataFrame.from_dict(levels, orient='index')
number_parents = pd.DataFrame.from_dict(number_parents, orient='index')

GO_terms_auc_log_df = pd.concat([GO_terms_auc_log_df, levels,number_parents], axis=1)
GO_terms_auc_log_df.columns = ["auc","levels","parents"]

sns.set(rc={'figure.figsize':(10,6)})
fig, ax = plt.subplots()
ax = sns.boxplot(x="levels", y="auc", data=GO_terms_auc_log_df)

plt.yticks(fontsize=16)
plt.xticks(fontsize=16)

ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)
ax.spines['left'].set_visible(False)
ax.spines['bottom'].set_color('#DDDDDD')

# Second, remove the ticks as well.
ax.tick_params(bottom=False, left=True)

# Third, add a horizontal grid (but keep the vertical grid hidden).
# Color the lines a light gray as well.
ax.set_axisbelow(True)
ax.yaxis.grid(True, color='#EEEEEE')
ax.xaxis.grid(False)

plt.xlabel("Level number", fontsize=20)
plt.ylabel("AUC value", fontsize=20)
plt.title("AUC value per level of GO hierarchy", fontsize=24)
# con el que mejor funciona es con la suma normal del attribution 
fig.tight_layout()
fig.savefig(resultsdir+'AUCbyLevelslog.png', transparent=True)

GO_terms_auc_log_df.head()

import pyreadr pyreadr.write_rdata(“C:/Users/ksada/OneDrive - Tecnun/SparseGO_Rdata/cv_allsamples_mutations/”+“GO_terms_auc_logarithm.RData”, GO_terms_auc_log_df.reset_index(), df_name=“GO_terms_auc_logarithm”)

TOP 15 PREDICTED GO TERMS

top15goterms= np.array(GO_terms_auc_log_df.sort_values(by=["auc"], ascending=False)[0:15].index)

Get Top GO term names

top15goterms_1 = []
for goterm in top15goterms:
    top15goterms_1.append(goterm+"_"+str(1))
real_go_info_mod_best = real_go_info[real_go_info.GO_term.isin(top15goterms_1)]
real_go_info_mod_best.GO_term = real_go_info_mod_best.GO_term.str.replace("_1","")

top15goterms_auc = GO_terms_auc_log_df.sort_values(by=["auc"], ascending=False)[0:15].reset_index()
top15goterms_auc.columns=["GO_term","auc","levels","parents"]

top15goterms_auc.merge(real_go_info_mod_best[real_go_info_mod_best["GO_term"].isin(top15goterms)], on="GO_term")

WORST 15 PREDICTED GO TERMS

worst15goterms= np.array(GO_terms_auc_log_df.sort_values(by=["auc"], ascending=True)[0:15].index)

Get Worst GO term names

worst15goterms_1 = []
for goterm in worst15goterms:
    worst15goterms_1.append(goterm+"_"+str(1))
real_go_info_mod_worst = real_go_info[real_go_info.GO_term.isin(worst15goterms_1)]
real_go_info_mod_worst.GO_term = real_go_info_mod_worst.GO_term.str.replace("_1","")

worst15goterms_auc = GO_terms_auc_log_df.sort_values(by=["auc"], ascending=True)[0:15].reset_index()
worst15goterms_auc.columns=["GO_term","auc","levels","parents"]

worst15goterms_auc.merge(real_go_info_mod_worst[real_go_info_mod_worst["GO_term"].isin(worst15goterms)], on="GO_term")

AUPR histogram

GO_terms_aupr_log_df = pd.DataFrame(list(GO_terms_aupr_log.items()),columns = ['goterm','aupr']).set_index("goterm")
GO_terms_aupr_log_df = GO_terms_aupr_log_df.dropna()
GO_terms_aupr_log_df.sort_values(by=["aupr"], ascending=False).head()

# TENGO PROBLEMA CON EL RECALL 
sns.set(rc={'figure.figsize':(5,3)})
perc = str(round((100*len(GO_terms_aupr_log_df[GO_terms_aupr_log_df["aupr"]>0.69])/len(GO_terms_aupr_log_df)),2))+"%"
N, bins, patches = plt.hist(GO_terms_aupr_log_df, color=CB_color_cycle[6],bins=50, linewidth=0.1)
for i in range(0,len(bins)-1):
    if bins[i]>0.69:
        patches[i].set_facecolor(CB_color_cycle[3])

plt.xlabel("AUPR", fontsize=16)  
plt.title(perc, fontsize=16)

Precision histogram

GO_terms_precision_log_df = pd.DataFrame(list(GO_terms_precision_log.items()),columns = ['goterm','precision']).set_index("goterm")
GO_terms_precision_log_df = GO_terms_precision_log_df.dropna()
GO_terms_precision_log_df.sort_values(by=["precision"], ascending=False).head()

perc = str(round((100*len(GO_terms_precision_log_df[GO_terms_precision_log_df["precision"]>0.69])/len(GO_terms_precision_log_df)),2))+"%"
N, bins, patches = plt.hist(GO_terms_precision_log_df, color=CB_color_cycle[6],bins=50, linewidth=0.1)

for i in range(0,len(bins)-1):
    if bins[i]>0.69:
        patches[i].set_facecolor(CB_color_cycle[4])

plt.xlabel("Precision", fontsize=16)  
plt.title(perc, fontsize=16)

Example prediction

def f2(goterm):    
    return goterm

combobox_go = interactive(f2, goterm=widgets.Combobox(options=list(GO_terms_auc_log_df.sort_values(by=["auc"], ascending=False).index)))

Choose drug to study…

display(combobox_go)

selected_go = combobox_go.result

#auc
fpr, tpr, _ = metrics.roc_curve(slim_matrix_single_neuron.loc[selected_go],  logits_matrix.loc[selected_go])
auc = metrics.roc_auc_score(slim_matrix_single_neuron.loc[selected_go],  logits_matrix.loc[selected_go])
plt.plot(fpr,tpr,label="data 1, auc="+str(auc))
plt.legend(loc=4)
plt.show()

plot = pd.concat([pd.DataFrame(slim_matrix_single_neuron.loc[selected_go]),pd.DataFrame(logits_matrix.loc[selected_go])], axis=1)
plot.columns = ["slim","probability"]
ax = sns.boxplot(x="slim", y="probability", data=plot,showfliers=False )

metrics.ConfusionMatrixDisplay.from_predictions(slim_matrix_single_neuron.loc[selected_go], preds_matrix.loc[selected_go])
plt.grid(b=None)
print("Accuracy:",metrics.accuracy_score(slim_matrix_single_neuron.loc[selected_go], preds_matrix.loc[selected_go]))
print("Precision:",metrics.precision_score(slim_matrix_single_neuron.loc[selected_go], preds_matrix.loc[selected_go]))
print("Recall:",metrics.recall_score(slim_matrix_single_neuron.loc[selected_go], preds_matrix.loc[selected_go])) #TP / (TP+FN)

TN - FP

FN - TP

precision, recall, thresholds = metrics.precision_recall_curve(slim_matrix_single_neuron.loc[selected_go],  logits_matrix.loc[selected_go])
auc_precision_recall = metrics.auc(recall, precision)
plt.plot(recall, precision,label=str(auc_precision_recall))
plt.legend(loc=4)
plt.show()

METRICS drugs

auc_drugs = {}
aupr_drugs = {}
for drug in list(slim_matrix_single_neuron.columns):
    if slim_matrix_single_neuron.loc[:,drug].sum() ==0:
        continue
    auc_drugs[drug] = metrics.roc_auc_score(slim_matrix_single_neuron.loc[:,drug],  logits_matrix.loc[:,drug])
    precision, recall, thresholds = metrics.precision_recall_curve(slim_matrix_single_neuron.loc[:,drug],  logits_matrix.loc[:,drug])
    aupr_drugs[drug] = metrics.auc(recall, precision)

auc_drugs_df = pd.DataFrame(list(auc_drugs.items()),columns = ['goterm','auc']).set_index("goterm")
auc_drugs_df = auc_drugs_df.dropna()

aupr_drugs_df = pd.DataFrame(list(aupr_drugs.items()),columns = ['goterm','aupr']).set_index("goterm")
aupr_drugs_df = aupr_drugs_df.dropna()

AUC histogram drugs

sns.set(rc={'figure.figsize':(10,6)})
fig, ax = plt.subplots()
perc = str(round((100*len(auc_drugs_df[auc_drugs_df["auc"]>0.69])/len(auc_drugs_df)),2))+"%"
N, bins, patches = plt.hist(auc_drugs_df, color=CB_color_cycle[6],bins=50, linewidth=0.1)

for i in range(0,len(bins)-1):
    if bins[i]>0.69:
        patches[i].set_facecolor(CB_color_cycle[5])

plt.yticks(fontsize=16)
plt.xticks(fontsize=16)

ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)
ax.spines['left'].set_visible(False)
ax.spines['bottom'].set_color('#DDDDDD')

# Second, remove the ticks as well.
ax.tick_params(bottom=False, left=True)

# Third, add a horizontal grid (but keep the vertical grid hidden).
# Color the lines a light gray as well.
ax.set_axisbelow(True)
ax.yaxis.grid(True, color='#EEEEEE')
ax.xaxis.grid(False)

plt.xlabel("AUC value", fontsize=20)
plt.ylabel("Number of drugs", fontsize=20)
colors2 = {'Drugs with AUC>=0.7':CB_color_cycle[5]}  
labels = list(colors2.keys())
handles = [plt.Rectangle((0,0),1,1, color=colors2[label]) for label in labels]
plt.legend(handles, labels,fontsize=20, loc="lower left", bbox_to_anchor=(0.35,-0.35))
plt.text(0.79, 6, str(perc), fontsize=20,color='#333333')
plt.title("Overall performance by drugs using mutations", fontsize=24)
# con el que mejor funciona es con la suma normal del attribution 
fig.tight_layout()
fig.savefig(resultsdir+'drugsAUClog.png', transparent=True)

auc_drugs_df.sort_values(by=["auc"], ascending=False)

AUPR histogram drugs

sns.set(rc={'figure.figsize':(5,3)})
perc = str(round((100*len(aupr_drugs_df[aupr_drugs_df["aupr"]>0.69])/len(aupr_drugs_df)),2))+"%"
N, bins, patches = plt.hist(aupr_drugs_df, color=CB_color_cycle[6],bins=50, linewidth=0.1)
for i in range(0,len(bins)-1):
    if bins[i]>0.69:
        patches[i].set_facecolor(CB_color_cycle[3])

plt.xlabel("AUPR drugs", fontsize=16)  
plt.title(perc, fontsize=16)

auc_drugs_df.sort_values(by=["auc"], ascending=False)

Example drug prediction

def f(drug):    
    return drug

combobox = interactive(f, drug=widgets.Combobox(options=list(auc_drugs_df.sort_values(by=["auc"], ascending=False).index)))

Choose drug to study…

display(combobox)

selected_drug_name = combobox.result

sns.set(rc={'figure.figsize':(4,2)})
#auc
fpr, tpr, _ = metrics.roc_curve(slim_matrix_single_neuron.loc[:,selected_drug_name], logits_matrix.loc[:,selected_drug_name] )
auc = metrics.roc_auc_score(slim_matrix_single_neuron.loc[:,selected_drug_name],  logits_matrix.loc[:,selected_drug_name])
plt.plot(fpr,tpr,label="data 1, auc="+str(auc))
plt.legend(loc=4)
plt.show()

plot = pd.concat([pd.DataFrame(slim_matrix_single_neuron.loc[:,selected_drug_name]),pd.DataFrame(logits_matrix.loc[:,selected_drug_name])], axis=1)
plot.columns = ["slim","probability"]
ax = sns.boxplot(x="slim", y="probability", data=plot,showfliers=False )

sum(slim_matrix_single_neuron.loc[:,selected_drug_name])

plot = pd.concat([pd.DataFrame(slim_matrix.loc[:,selected_drug_name]),pd.DataFrame(attribution_data_all.loc[:,selected_drug_name]*1e4)], axis=1)
plot.columns = ["slim","attribution"]
ax = sns.boxplot(x="slim", y="attribution", data=plot,showfliers=True )

metrics.ConfusionMatrixDisplay.from_predictions(slim_matrix_single_neuron.loc[:,selected_drug_name], preds_matrix.loc[:,selected_drug_name])
plt.grid(visible=None)
print("Accuracy:",metrics.accuracy_score(slim_matrix_single_neuron.loc[:,selected_drug_name], preds_matrix.loc[:,selected_drug_name]))
print("Precision:",metrics.precision_score(slim_matrix_single_neuron.loc[:,selected_drug_name], preds_matrix.loc[:,selected_drug_name]))
print("Recall:",metrics.recall_score(slim_matrix_single_neuron.loc[:,selected_drug_name], preds_matrix.loc[:,selected_drug_name])) #TP / (TP+FN)
print("AUC with score:",auc) #TP / (TP+FN)

View drug’s top functions…

predictions_nodes = []
for goterm in list(logits_matrix.index):
    predictions_nodes.append(goterm+"_"+str(1))

# add names to go terms
real_go_info_log = real_go_info[real_go_info.GO_term.isin(predictions_nodes)]
real_go_info_log.GO_term = real_go_info_log.GO_term.str.replace("_1","")

# LOS LOGITS DE TEST!!
test_drug_logs = pd.DataFrame(logits_matrix.loc[:,selected_drug_name]).reset_index()
test_drug_logs.columns  = ["GO_term","probability"]
test_drug_logs = test_drug_logs.merge(real_go_info_log, on="GO_term")
test_drug_logs.sort_values(by=["probability"], ascending=False)

sns.set(rc={'figure.figsize':(15,8)})
ax = sns.boxplot(x="layer_number", y="probability", data=test_drug_logs, order=[7,6,5,4,3,2,1,0],showfliers=False)
ax = ax.set(xlabel='General terms                                                    -                                                          Specific terms')

Final model

Once the models have been cross-validated we create the final models using all samples…

GO_terms_auc_log_final = {}
GO_terms_aupr_log_final = {}
GO_terms_precision_log_final = {}
models_log = {}

# Perform logistics
for goterm in sparseGO_terms:
    #print(goterm)
    goterm_drugs = slim_matrix.loc[[goterm+"_"+str(1)]].values.flatten()
    
    if sum(goterm_drugs) <= 10:
        continue

    list_nodes = []
    for i in range(1,7):
        list_nodes.append(goterm+"_"+str(i))

    score = attribution_data_annotated.loc[list_nodes].T
    score_mod = score.divide(score.std()).fillna(0)
    
    # train and test are the same 
    X_train = score_mod
    X_test = score_mod
    y_train = goterm_drugs
    y_test = goterm_drugs
    
    logreg = LogisticRegression(penalty="l2",solver="liblinear",max_iter=2000, C=10e-2,class_weight="balanced")
    # fit the model with data
    logreg.fit(X_train,y_train)
    y_pred=logreg.predict(X_test)

    #auc
    y_pred_proba = logreg.predict_proba(X_test)[::,1]
    GO_terms_auc_log_final[goterm] = metrics.roc_auc_score(y_test, y_pred_proba)

    precision, recall, thresholds = metrics.precision_recall_curve(y_test, y_pred_proba)
    GO_terms_aupr_log_final[goterm] = metrics.auc(recall, precision)
    GO_terms_precision_log_final[goterm] = metrics.recall_score(y_test, y_pred)
    models_log[goterm]=logreg

len(models_log)

Final model AUC

GO_terms_auc_log_df_final = pd.DataFrame(list(GO_terms_auc_log_final.items()),columns = ['goterm','auc']).set_index("goterm")
GO_terms_auc_log_df_final = GO_terms_auc_log_df_final.dropna()
GO_terms_auc_log_df_final.sort_values(by=["auc"], ascending=False)

sns.set(rc={'figure.figsize':(6,4)})
perc = str(round((100*len(GO_terms_auc_log_df_final[GO_terms_auc_log_df_final["auc"]>0.7])/len(GO_terms_auc_log_df_final)),2))+"%"
N, bins, patches = plt.hist(GO_terms_auc_log_df_final, color=CB_color_cycle[6],bins=50, linewidth=0.1)

for i in range(0,len(bins)-1):
    if bins[i]>0.7:
        patches[i].set_facecolor(CB_color_cycle[2])

plt.xlabel("AUC (logistic 1)", fontsize=16)  
plt.title(perc, fontsize=16)
# con el que mejor funciona es con la suma normal del attribution 

Final model AUPR

GO_terms_aupr_log_df_final = pd.DataFrame(list(GO_terms_aupr_log_final.items()),columns = ['goterm','aupr']).set_index("goterm")
GO_terms_aupr_log_df_final = GO_terms_aupr_log_df_final.dropna()
GO_terms_aupr_log_df_final.sort_values(by=["aupr"], ascending=False).head()

# TENGO PROBLEMA CON EL RECALL 
sns.set(rc={'figure.figsize':(5,3)})
perc = str(round((100*len(GO_terms_aupr_log_df_final[GO_terms_aupr_log_df_final["aupr"]>0.7])/len(GO_terms_aupr_log_df_final)),2))+"%"
N, bins, patches = plt.hist(GO_terms_aupr_log_df_final, color=CB_color_cycle[6],bins=50, linewidth=0.1)
for i in range(0,len(bins)-1):
    if bins[i]>0.7:
        patches[i].set_facecolor(CB_color_cycle[3])

plt.xlabel("AUPR", fontsize=16)  
plt.title(perc, fontsize=16)

Final model Recall

GO_terms_precision_log_df_final = pd.DataFrame(list(GO_terms_precision_log_final.items()),columns = ['goterm','precision']).set_index("goterm")
GO_terms_precision_log_df_final = GO_terms_precision_log_df_final.dropna()
GO_terms_precision_log_df_final.sort_values(by=["precision"], ascending=False).head()

perc = str(round((100*len(GO_terms_precision_log_df_final[GO_terms_precision_log_df_final["precision"]>0.69])/len(GO_terms_precision_log_df_final)),2))+"%"
N, bins, patches = plt.hist(GO_terms_precision_log_df_final, color=CB_color_cycle[6],bins=50, linewidth=0.1)

for i in range(0,len(bins)-1):
    if bins[i]>0.69:
        patches[i].set_facecolor(CB_color_cycle[4])

plt.xlabel("Recall", fontsize=16)  
plt.title(perc, fontsize=16)

Predict for a new drug

Make predictions

unknown = list(set(attribution_data_all.columns)-set(attribution_data_annotated.columns))

Get the probabilities for all unknown drugs

predictions = {}
probabilities = {}
probabilities_unknown = pd.DataFrame()

for drug in unknown:
    for goterm in models_log.keys():

        list_nodes = list(models_log[goterm].feature_names_in_) # Extract the feature names from the model (those are the attributions we need)

        score = attribution_data_all.loc[list_nodes][drug].to_frame().T 
        score_mod = score.divide(attribution_data_annotated.loc[list_nodes].T.std()).fillna(0) #divide by std of each neuron, only use drugs that trained the models

        #predictions[goterm]=models_log[goterm].predict(score_mod)

        #auc
        probabilities[goterm] = models_log[goterm].predict_proba(score_mod)[::,1]

        drug_probs = pd.DataFrame.from_dict(probabilities).T
        drug_probs.columns = [drug]
        
    print(drug)
    probabilities_unknown = pd.concat([probabilities_unknown,drug_probs], axis=1)

# Save file
with open(resultsdir+'probabilities_unknown_MG2_log_sum.pkl', 'wb') as dictionary_file:
  pickle.dump(probabilities_unknown, dictionary_file)

IMPORT file

# To import dataframe created before
with open(resultsdir+'probabilities_unknown_MG2_log_sum.pkl', 'rb') as dictionary_file:
    probabilities_unknown = pickle.load(dictionary_file)  

import pyreadr pyreadr.write_rdata(“C:/Users/ksada/OneDrive - Tecnun/SparseGO_Rdata/cv_allsamples_mutations/”+“probabilities_known.RData”, probabilities_unknown.reset_index(), df_name=“probabilities_known”)

Study drug with unknown MOA

Choose drug with unknown MOA…

combobox_u = interactive(f, drug=widgets.Combobox(options=unknown))

display(combobox_u)

selected_drug_u_name = combobox_u.result

probabilities_df = pd.DataFrame.from_dict(probabilities_unknown.loc[:,selected_drug_u_name]).reset_index()
probabilities_df.columns  = ["GO_term","probability"]
probabilities_df = probabilities_df.merge(real_go_info_log, on="GO_term")
probabilities_df.sort_values(by=["probability"], ascending=False)

sns.set(rc={'figure.figsize':(15,8)})
ax = sns.boxplot(x="layer_number", y="probability", data=probabilities_df, order=[7,6,5,4,3,2,1,0],showfliers=False)
ax = ax.set(xlabel='General terms                                                    -                                                          Specific terms')

• bendamustine –> buen ejemplo, parece que tiene sentido lo que sale, es un farmaco para la leucemia y salen cosas de la sangre https://pubchem.ncbi.nlm.nih.gov/compound/65628#section=Chemical-Vendors
• temozolomide –> es para Glioblastoma y me sale brain de los más altos y algo de calcium que tiene algo que ver
• Bleomycin –>

Look for the GO terms (neurons) that vary the most variance between drugs…

# Attribution
topvariance = list(attribution_data_all.var(axis=1).sort_values(axis=0, ascending=False)[0:100].index.values)
data_array = attribution_data_all.loc[topvariance].T

Or cluster by the probability…

# Probabilities
topvariance = list(probabilities_unknown.var(axis=1).sort_values(axis=0, ascending=False)[0:200].index.values)
data_array = probabilities_unknown.loc[topvariance].T

import plotly.graph_objects as go
import plotly.figure_factory as ff
from scipy.spatial.distance import pdist, squareform

# get data
labelsGOterms = np.array(data_array.columns)
labelsDrugs = np.array(data_array.index)

# Initialize figure by creating upper dendrogram
fig = ff.create_dendrogram(data_array.T, orientation='bottom',labels=labelsGOterms)
for i in range(len(fig['data'])):
    fig['data'][i]['yaxis'] = 'y2'

# Create Side Dendrogram
dendro_side = ff.create_dendrogram(data_array, orientation='right',labels=labelsDrugs)
for i in range(len(dendro_side['data'])):
    dendro_side['data'][i]['xaxis'] = 'x2'

# Add Side Dendrogram Data to Figure
for data in dendro_side['data']:
    fig.add_trace(data)

# Create Heatmap

heatmap = [
    go.Heatmap(
        x = fig['layout']['xaxis']['ticktext'],
        y = dendro_side['layout']['yaxis']['ticktext'],
        z = data_array.loc[dendro_side['layout']['yaxis']['ticktext'],fig['layout']['xaxis']['ticktext']],
         zmin=0, zmax=1
    )
]

heatmap[0]['x'] = fig['layout']['xaxis']['tickvals']
heatmap[0]['y'] = dendro_side['layout']['yaxis']['tickvals']

# Add Heatmap Data to Figure
for data in heatmap:
    fig.add_trace(data)

fig['layout']['yaxis']['ticktext'] = dendro_side['layout']['yaxis']['ticktext']
fig['layout']['yaxis']['tickvals'] = np.asarray(dendro_side['layout']['yaxis']['tickvals'])
    
# Edit Layout
fig.update_layout({'width':800, 'height':1100,
                         'showlegend':False, 'hovermode': 'closest',
                         })
# Edit xaxis
fig.update_layout(xaxis={'domain': [.15, 1],
                                  'mirror': False,
                                  'showgrid': False,
                                  'showline': False,
                                  'zeroline': False,
                                  'ticks':""})
# Edit xaxis2
fig.update_layout(xaxis2={'domain': [0, .15],
                                   'mirror': False,
                                   'showgrid': False,
                                   'showline': False,
                                   'zeroline': False,
                                   'showticklabels': False,
                                   'ticks':""})

# Edit yaxis
fig.update_layout(yaxis={'domain': [0, .85],
                                  'mirror': False,
                                  'showgrid': False,
                                  'showline': False,
                                  'zeroline': False,
                                  'showticklabels': False,
                                  'ticks': ""
                        })
# Edit yaxis2
fig.update_layout(yaxis2={'domain':[.825, .975],
                                   'mirror': False,
                                   'showgrid': False,
                                   'showline': False,
                                   'zeroline': False,
                                   'showticklabels': False,
                                   'ticks':""})

# Plot!
fig.show()

Dendograms - Most commonly created as an output from hierarchical clustering. - The key to interpreting is to focus on the height at which any two objects are joined together. When the height of the link that joins the rows together is the smallest, their are the most similar. - Gives an idea of the number of clusters (but can’t determine the number).

from scipy.stats import ranksums 
GO_terms_wilcox = {}
number_ones_w = {}
sum_attribution = {}
#terms_direct_genes = {}
terms_all_genes = {}
# Perform wilcox
for goterm in slim_matrix.index:
    goterm_drugs = slim_matrix.loc[[goterm]].T
    goterm_drugs.columns = ["slim"]
    score = attribution_data_all.loc[[goterm]].T
    score.columns = ["score"]
    slim_score = goterm_drugs.join(score)
    slim_score.columns = ["slim","score"]
    number_ones_w[goterm] = sum(goterm_drugs.values.flatten())
    sum_attribution[goterm] = sum(score.values.flatten())
    #terms_direct_genes[goterm]=len(term_direct_gene_map[goterm[:-2]])
    terms_all_genes[goterm]=(term_size_map[goterm[:-2]])
    GO_terms_wilcox[goterm] = ranksums(slim_score.loc[slim_score["slim"] == 1]["score"], slim_score.loc[slim_score["slim"] == 0]["score"]).pvalue
    #GO_terms_wilcox[goterm] = ranksums(slim_score.loc[slim_score["slim"] == 1]["score"], slim_score.loc[slim_score["slim"] == 0]["score"],alternative="greater").pvalue

GO_terms_wilcox_df = pd.DataFrame(list(GO_terms_wilcox.items()),columns = ['goterm','score']).set_index("goterm")
GO_terms_wilcox_df = GO_terms_wilcox_df.dropna()
GO_terms_wilcox_df.sort_values(by=["score"], ascending=True)

GO_terms_wilcox_df

Percentage lower than 0.05…

perc = str(round((100*len(GO_terms_wilcox_df[GO_terms_wilcox_df["score"]<0.05])/len(GO_terms_wilcox_df)),2))+"%"

sns.set(rc={'figure.figsize':(5,3)})
#sns.histplot(data=GO_terms_wilcox_df, x="score", kde=True, color="olive", bins=100).set(title='Wilcox GO terms - '+perc)
histogram(GO_terms_wilcox_df["score"],CB_color_cycle[0],'Wilcox GO terms - '+perc,"Number of GO terms",n_bins=200)

Draw

goterm="GO:1903077_1"
slim = slim_matrix.loc[[goterm]].T
slim.columns = ["slim"]
score = attribution_data_annotated.loc[[goterm]].T
score.columns = ["score"]
score.index = slim.index
plot = slim.join(score)
plot.columns = ["slim","score"]
ax = sns.boxplot(x="slim", y="score", data=plot )

# Plotting the KDE Plot
sns.kdeplot(plot.loc[plot["slim"] == 1]["score"], color='orange', shade=True, label=1)
sns.kdeplot(plot.loc[plot["slim"] == 0]["score"], color='blue', shade=True, label=0)
plt.xlabel('Attribution')
plt.ylabel('Probability Density')

slim.sum()

len(plot)

esta no tiene sentido si no es absoluto el valor (porque puede afectar o positiva o negativamente el attribution)

from scipy.stats import ranksums 

drugs_wilcox = {}
# Perform wilcox
number_parents = {}
levels = {}
for i in range(0,len(slim_matrix.index)):
    term = slim_matrix.index[i][:-2]
    number_parents[slim_matrix.index[i]]=len([source for source, _ in  dG.in_edges(term)])
    levels[slim_matrix.index[i]]=level_number[term]-1
levels = pd.DataFrame.from_dict(levels, orient='index')
number_parents = pd.DataFrame.from_dict(number_parents, orient='index')

for drug in slim_matrix.columns:
    slim_score = pd.concat([slim_matrix[drug], attribution_data_all[drug],levels], axis=1)
    slim_score.columns = ["slim","score","levels"]
    #slim_score = slim_score.loc[slim_score["levels"] != 7]
    drugs_wilcox[drug] = ranksums(slim_score.loc[slim_score["slim"] == 1]["score"], slim_score.loc[slim_score["slim"] == 0]["score"]).pvalue
    #drugs_wilcox[drug] = ranksums(slim_score.loc[slim_score["slim"] == 1]["score"], slim_score.loc[slim_score["slim"] == 0]["score"],alternative="greater").pvalue

drugs_wilcox_df = pd.DataFrame(list(drugs_wilcox.items()),columns = ['goterm','score']).set_index("goterm")
drugs_wilcox_df = drugs_wilcox_df.dropna()
drugs_wilcox_df.sort_values(by=["score"], ascending=True)

len(drugs_wilcox_df[drugs_wilcox_df["score"]<0.05])

len(drugs_wilcox_df)

perc = str(round(100*(len(drugs_wilcox_df[drugs_wilcox_df["score"]<0.05])/len(drugs_wilcox_df)),2))+"%"

sns.set(rc={'figure.figsize':(4,4)})
histogram(drugs_wilcox_df["score"],CB_color_cycle[1],'Wilcox Drugs - '+perc,"Number of Drugs",n_bins=10)

Draw

drug="selumetinib"

plot = pd.concat([slim_matrix[drug], attribution_data_all[drug],number_parents,levels],axis=1)
plot.columns = ["slim","score","parents","levels"]

sns.set(rc={'figure.figsize':(4,4)})
ax = sns.boxplot(x="slim", y="score", data=plot,showfliers=True )

ranksums(plot.loc[plot["slim"] == 1]["score"], plot.loc[plot["slim"] == 0]["score"]).pvalue

sns.set(rc={'figure.figsize':(15,8)})
ax = sns.boxplot(x="levels", y="score", hue="slim", data=plot, order=[7,6,5,4,3,2,1,0])
ax = ax.set(xlabel='General terms                                                    -                                                          Specific terms')

vals = list()
for i in range(0,8):
    plot_level = plot.loc[plot["levels"] == i]
    pvalue = ranksums(plot_level.loc[plot_level["slim"] == 1]["score"], plot_level.loc[plot_level["slim"] == 0]["score"]).pvalue
    vals.append(pvalue) 
    print("P-value level "+str(i)+": "+str(pvalue))

    
from scipy.stats import combine_pvalues
cleanedvals  = [x for x in vals if ~np.isnan(x)] # delete nans, some levels have only 1 class
combine_pvalues(cleanedvals,method='fisher',weights=None)

sns.set(rc={'figure.figsize':(20,8)})
ax = sns.boxplot(x="parents", y="score", hue="slim", data=plot)

len(plot.loc[plot["slim"] == 1])/6

len(plot.loc[plot["slim"] == 0])/6

Wilcox by layers and add by fisher

from scipy.stats import ranksums, combine_pvalues

drugs_wilcox_levels = {}
# Perform wilcox
for drug in slim_matrix.columns:
    slim_score = pd.concat([slim_matrix[drug], attribution_data_all[drug],number_parents,levels], axis=1)
    slim_score.columns = ["slim","score","parents","levels"]
    
    vals = list()
    for i in range(1,27):
        slim_score_level = slim_score.loc[slim_score["parents"] == i]
        pvalue = ranksums(slim_score_level.loc[slim_score_level["slim"] == 1]["score"], slim_score_level.loc[slim_score_level["slim"] == 0]["score"]).pvalue
        vals.append(pvalue) 
        
    cleanedvals  = [x for x in vals if ~np.isnan(x)] # delete nans, some levels have only 1 class
    s, drugs_wilcox_levels[drug] = combine_pvalues(cleanedvals,method='fisher',weights=None)
    print(drug)

slim_score

drugs_wilcox_levels_df = pd.DataFrame(list(drugs_wilcox_levels.items()),columns = ['goterm','score']).set_index("goterm")
drugs_wilcox_levels_df = drugs_wilcox_levels_df.dropna()
drugs_wilcox_levels_df.sort_values(by=["score"], ascending=True)

sns.set(rc={'figure.figsize':(4,4)})
perc = str(round(100*(len(drugs_wilcox_levels_df[drugs_wilcox_levels_df["score"]<0.05])/len(drugs_wilcox_levels_df)),2))+"%"
histogram(drugs_wilcox_levels_df["score"],CB_color_cycle[1],'Wilcox Drugs - '+perc,"Number of Drugs",n_bins=10)

len(slim_matrix.columns)

SVM

from sklearn.model_selection import train_test_split
from sklearn import metrics
from sklearn.linear_model import LogisticRegression

from sklearn import svm

slim_matrix_single_neuron = pd.DataFrame(0, index=sparseGO_terms, columns=slim_matrix.columns)
preds_svm_matrix = pd.DataFrame(0, index=sparseGO_terms, columns=slim_matrix.columns)
platt_matrix = pd.DataFrame(0, index=sparseGO_terms, columns=slim_matrix.columns)
distance_matrix = pd.DataFrame(0, index=sparseGO_terms, columns=slim_matrix.columns)
delta_logits_matrix  = pd.DataFrame(0, index=sparseGO_terms, columns=slim_matrix.columns)

Create models

Regression models…

# Dictionaries to store results
GO_terms_auc_svm = {}
GO_terms_aupr_svm = {}
GO_terms_precision_svm = {}
GO_terms_auc_delta_logits = {}

# Perform logistic
for goterm in sparseGO_terms:
    # if (real_go_info[real_go_info["GO_term"]==goterm+"_1"]["layer_number"]).values >3:
    #     continue
    
    # store results of each cross validation
    all_y_test = []
    all_y_pred_proba = []
    all_y_pred_proba_dis = []
    all_y_pred = []
    all_y_names = []

    goterm_drugs = slim_matrix.loc[[goterm+"_"+str(1)]].values.flatten()

    if sum(goterm_drugs) <= 8: # at least 2 annotated drugs in each group
            continue

    list_nodes = []
    for i in range(1,7):
        list_nodes.append(goterm+"_"+str(i))

    score = attribution_data_annotated.loc[list_nodes].T
    #score_mod = score
    score_mod = score.divide(score.std()).fillna(0) # AFECTA MUCHO

    # Separate drugs in 4 groups for cross-validation -----

    # Split data in 2 groups (with train_test_split in order to have 0s in both groups)
    X_part1,X_part2,y_part1,y_part2=train_test_split(score_mod,goterm_drugs,test_size=0.50,random_state=0,stratify=goterm_drugs)
    # Split data again in 4 groups (split data previously split)
    X_group1,X_group2,y_group1,y_group2=train_test_split(X_part1,y_part1,test_size=0.50,random_state=0,stratify=y_part1)
    X_group3,X_group4,y_group3,y_group4=train_test_split(X_part2,y_part2,test_size=0.50,random_state=0,stratify=y_part2)

    for i in  range(1,5):
        vector = range(0,5)
        group_number = str(i)
        X_test = globals()["X_group"+group_number]
        y_test = globals()["y_group"+group_number]

        # Use the other 3 groups for training 
        keep = list({1,2,3,4}-{int(group_number)}) # remove group number of current test 
        X_train = pd.concat((globals()["X_group"+str(keep[0])],globals()["X_group"+str(keep[1])],globals()["X_group"+str(keep[2])]))
        y_train = np.concatenate((globals()["y_group"+str(keep[0])],globals()["y_group"+str(keep[1])],globals()["y_group"+str(keep[2])]))
        
        #gamma = 1/(X_train.shape[1]*X_train.to_numpy().var())
        gamma = "scale"
        C=1
        
        svm_model = svm.SVC(C=C,gamma=gamma, kernel='rbf',
                           class_weight="balanced",
                            tol=0.001,
                            probability=True,
                            random_state=1234)
        # svm_model = svm.SVC(gamma='auto', kernel='rbf',class_weight="balanced",probability=True)
        
        # fit the model with data
        svm_model.fit(X_train,y_train)
        y_pred=svm_model.predict(X_test)
        y_pred_proba = svm_model.predict_proba(X_test)[::,1] # platt values
        y_pred_proba_dis = svm_model.decision_function(X_test) # An SVM returns a real-valued prediction for each of the input data samples, which corresponds to its distance from the separating hyperplane.
        #  decision_function SORTS the results from most probable class to the least probable one.
        
        all_y_test.append(y_test)
        all_y_pred_proba.append(y_pred_proba)
        all_y_pred_proba_dis.append(y_pred_proba_dis)
        all_y_pred.append(y_pred)
        all_y_names.append(X_test.index)

    all_y_test = np.concatenate(all_y_test)
    all_y_pred_proba = np.concatenate(all_y_pred_proba)
    all_y_pred_proba_dis = np.concatenate(all_y_pred_proba_dis)
    all_y_names = np.concatenate(all_y_names)
    all_y_pred = np.concatenate(all_y_pred)
    
    percentage_go_annotations = sum(all_y_test)/len(all_y_test)
    logits_apriori=np.log(percentage_go_annotations/(1-percentage_go_annotations))
    logits_apost= np.log(all_y_pred_proba/(1-all_y_pred_proba))
    delta_logits = logits_apost-logits_apriori

    platt_matrix.loc[goterm,all_y_names] = all_y_pred_proba
    distance_matrix.loc[goterm,all_y_names] = all_y_pred_proba_dis
    slim_matrix_single_neuron.loc[goterm,all_y_names] = all_y_test
    preds_svm_matrix.loc[goterm,all_y_names] = all_y_pred
    
    delta_logits_matrix.loc[goterm,all_y_names] = delta_logits

    GO_terms_auc_delta_logits[goterm] = metrics.roc_auc_score(all_y_test, delta_logits)
    GO_terms_auc_svm[goterm] = metrics.roc_auc_score(all_y_test, all_y_pred_proba)

    precision, recall, thresholds = metrics.precision_recall_curve(all_y_test, all_y_pred_proba)
    GO_terms_aupr_svm[goterm] = metrics.auc(recall, precision)
    GO_terms_precision_svm[goterm] = metrics.precision_score(all_y_test, all_y_pred)

# done with platt values
GO_terms_auc_svm_df = pd.DataFrame(list(GO_terms_auc_svm.items()),columns = ['goterm','auc']).set_index("goterm")
GO_terms_auc_svm_df = GO_terms_auc_svm_df.dropna()
GO_terms_auc_svm_df.sort_values(by=["auc"], ascending=False).head()

	auc
goterm
GO:0036289	0.999708
GO:0060440	0.994743
GO:0042149	0.971292
GO:1902455	0.969545
GO:0001556	0.965979

print("There are " +str(len(GO_terms_auc_svm_df))+ " svm models.")

There are 939 svm models.

# only keep goterms that have a model 
platt_matrix = platt_matrix.loc[list(GO_terms_auc_svm_df.index),:]
distance_matrix = distance_matrix.loc[list(GO_terms_auc_svm_df.index),:]
slim_matrix_single_neuron  = slim_matrix_single_neuron.loc[list(GO_terms_auc_svm_df.index),:]
preds_svm_matrix  = preds_svm_matrix.loc[list(GO_terms_auc_svm_df.index),:]
delta_logits_matrix  = delta_logits_matrix.loc[list(GO_terms_auc_svm_df.index),:]

AUC histogram

sns.set(rc={'figure.figsize':(10,6)})
fig, ax = plt.subplots()
perc = str(round((100*len(GO_terms_auc_svm_df[GO_terms_auc_svm_df["auc"]>0.69])/len(GO_terms_auc_svm_df)),2))+"%"
N, bins, patches = plt.hist(GO_terms_auc_svm_df, color=CB_color_cycle[6],bins=50, linewidth=0.1)

for i in range(0,len(bins)-1):
    if bins[i]>0.69:
        patches[i].set_facecolor(CB_color_cycle[2])

plt.yticks(fontsize=16)
plt.xticks(fontsize=16)

ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)
ax.spines['left'].set_visible(False)
ax.spines['bottom'].set_color('#DDDDDD')

# Second, remove the ticks as well.
ax.tick_params(bottom=False, left=True)

# Third, add a horizontal grid (but keep the vertical grid hidden).
# Color the lines a light gray as well.
ax.set_axisbelow(True)
ax.yaxis.grid(True, color='#EEEEEE')
ax.xaxis.grid(False)

plt.xlabel("AUC value", fontsize=20)
plt.ylabel("Number of GO term models", fontsize=20)
colors2 = {'GO term models with AUC>=0.7':CB_color_cycle[2]}  
labels = list(colors2.keys())
handles = [plt.Rectangle((0,0),1,1, color=colors2[label]) for label in labels]
plt.legend(handles, labels,fontsize=20, loc="lower left", bbox_to_anchor=(0.35,-0.35))
plt.text(0.71, 8, str(perc), fontsize=20,color='#333333')
plt.title("Overall performance of the models using expression", fontsize=24)
# con el que mejor funciona es con la suma normal del attribution 
fig.tight_layout()
fig.savefig(resultsdir+'modelsAUCsvm.png', transparent=True)

AUC waterfall plot

GO_terms_auc_svm_df =GO_terms_auc_svm_df.sort_values(by=["auc"], ascending=False)

plt.rcParams['figure.figsize'] = (12, 9)
drugs = GO_terms_auc_svm_df.index
rhos = GO_terms_auc_svm_df["auc"]

percentage = round((sum(rhos>0.69)/len(rhos))*100,1)

fig, ax = plt.subplots()
#colors = ['#208EA3' if (x < 0.5) else '#A4C61A' for x in rhos ]
colors = ['#C9C9C9' if (x < 0.69) else "#6492CA" for x in rhos ]
ax.bar(
    x=drugs,
    height=rhos,
    edgecolor=colors,
    linewidth=2
)
plt.xticks([])
plt.yticks(fontsize=28)


# First, let's remove the top, right and left spines (figure borders)
# which really aren't necessary for a bar chart.
# Also, make the bottom spine gray instead of black.
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)
ax.spines['left'].set_visible(False)
ax.spines['bottom'].set_visible(False)
#ax.spines['bottom'].set_color('#DDDDDD')

# Second, remove the ticks as well.
ax.tick_params(bottom=False, left=False)

# Third, add a horizontal grid (but keep the vertical grid hidden).
# Color the lines a light gray as well.
ax.set_axisbelow(False)
ax.yaxis.grid(False)
#ax.yaxis.grid(True, color='#EEEEEE')
ax.xaxis.grid(False)


# Add labels and a title. Note the use of `labelpad` and `pad` to add some
# extra space between the text and the tick labels.
ax.set_xlabel('SVM models', labelpad=-30, color='#333333',fontsize=50)
ax.set_ylabel('AUC-ROC value', labelpad=15, color='#333333',fontsize=50)
ax.set_title('', color='#333333',
             weight='bold')

colors2 = {'High confidence drugs (r>0.5)':'#A4C61A'}  
labels = list(colors2.keys())
handles = [plt.Rectangle((0,0),1,1, color=colors2[label]) for label in labels]
#plt.legend(handles, labels,fontsize=40, loc="lower left",bbox_to_anchor=(0, -0.215))
plt.text(77, 0.32, str(percentage)+"%", fontsize=60,color='#000000')

plt.ylim((-0.1,1.1))
# Make the chart fill out the figure better.
fig.tight_layout()
fig.savefig(resultsdir+'WaterfallModelsSVM.png', transparent=True)

AUC boxplot by parents

# Add number of parents
number_parents = {}
levels = {}
for i in range(0,len(GO_terms_auc_svm_df.index)):
    term = GO_terms_auc_svm_df.index[i]
    number_parents[GO_terms_auc_svm_df.index[i]]=len([source for source, _ in  dG.in_edges(term)])
    levels[GO_terms_auc_svm_df.index[i]]=level_number[term]-1
levels = pd.DataFrame.from_dict(levels, orient='index')
number_parents = pd.DataFrame.from_dict(number_parents, orient='index')

GO_terms_auc_svm_df = pd.concat([GO_terms_auc_svm_df, levels,number_parents], axis=1)
GO_terms_auc_svm_df.columns = ["auc","levels","parents"]

GO_terms_auc_svm_df.head()

	auc	levels	parents
GO:0000077	0.284021	1	3
GO:0045737	0.835954	0	8
GO:0000082	0.732331	2	4
GO:1900087	0.593301	0	10
GO:2000134	0.865329	1	9

import plotly.express as px

c = ['#E8384F', '#FD817D', '#FDAE33',
         '#EECC16', '#A4C61A', '#37A862',"#208EA3","#3B6EAB"]

df = px.data.tips()
fig = px.box(GO_terms_auc_svm_df, x="levels", y="auc",
             color="levels",
            color_discrete_sequence=c,
             width =600,
             height=400,
              template="simple_white",
              labels=dict(levels="Level of GO hierarchy", auc="AUC-ROC")
            )
fig.update_traces(width=0.9)

fig.add_shape( # add a horizontal "target" line
    type="line", line_color="salmon", line_width=3, opacity=1, line_dash="dot",
    x0=0, x1=1, xref="paper", y0=0.7, y1=0.7, yref="y"
)


fig.update_layout(
   title=dict(text="<b> AUC value grouped by level of GO hierarchy <b>",
             x=0.5,
             y=0.9,
              font=dict(size=18),
              xanchor='center',
              yanchor='top'),
    xaxis=dict(ticks="", showticklabels=False, showgrid=False, zeroline=False),
    yaxis=dict(ticks="", showticklabels=True, showgrid=True, zeroline=False),
 #   yaxis_range=[min(yy.flatten()),max(yy.flatten())],
  #  xaxis_range=[min(xx.flatten()),max(xx.flatten())],
    legend=dict(x=1.1, y=1, orientation="v",font=dict(size=11)),
    paper_bgcolor='rgba(0,0,0,0)',
    font=dict(family='Roboto',color= "#36382E",size=15)
    )

fig.show()

TOP 15 PREDICTED GO TERMS

top15goterms= np.array(GO_terms_auc_svm_df.sort_values(by=["auc"], ascending=False)[0:15].index)

Get Top GO term names

top15goterms_1 = []
for goterm in top15goterms:
    top15goterms_1.append(goterm+"_"+str(1))
real_go_info_mod_best = real_go_info[real_go_info.GO_term.isin(top15goterms_1)]
real_go_info_mod_best.GO_term = real_go_info_mod_best.GO_term.str.replace("_1","")

top15goterms_auc = GO_terms_auc_svm_df.sort_values(by=["auc"], ascending=False)[0:15].reset_index()
top15goterms_auc.columns=["GO_term","auc","levels","parents"]

top15goterms_auc = top15goterms_auc.merge(real_go_info_mod_best[real_go_info_mod_best["GO_term"].isin(top15goterms)], on="GO_term")

top15goterms_auc

	GO_term	auc	levels	parents	Name	layer_number
0	GO:0036289	0.999708	0	2	Peptidyl-serine autophosphorylation (1)	0.0
1	GO:0060440	0.994743	0	4	Trachea formation (1)	0.0
2	GO:0042149	0.971292	0	1	Cellular response to glucose starvation (1)	0.0
3	GO:1902455	0.969545	0	2	Negative regulation of stem cell population maintenance (1)	0.0
4	GO:0001556	0.965979	0	6	Oocyte maturation (1)	0.0
5	GO:0045636	0.955115	0	6	Positive regulation of melanocyte differentiation (1)	0.0
6	GO:0010750	0.955000	0	4	Positive regulation of nitric oxide mediated signal transduction (1)	0.0
7	GO:0060020	0.949434	0	1	Bergmann glial cell differentiation (1)	0.0
8	GO:1902042	0.945804	0	4	Negative regulation of extrinsic apoptotic signaling pathway via death domain receptors (1)	0.0
9	GO:1902236	0.941667	0	12	Negative regulation of endoplasmic reticulum stress-induced intrinsic apoptotic signaling pathway (1)	0.0
10	GO:0070059	0.936432	1	2	Intrinsic apoptotic signaling pathway in response to endoplasmic reticulum stress (1)	1.0
11	GO:0051453	0.935521	1	2	Regulation of intracellular ph (1)	1.0
12	GO:0042659	0.931364	0	3	Regulation of cell fate specification (1)	0.0
13	GO:0006360	0.930046	2	7	Transcription by rna polymerase i (1)	2.0
14	GO:0006959	0.921730	2	2	Humoral immune response (1)	2.0

WORST 15 PREDICTED GO TERMS

worst15goterms= np.array(GO_terms_auc_svm_df.sort_values(by=["auc"], ascending=True)[0:15].index)

Get Worst GO term names

worst15goterms_1 = []
for goterm in worst15goterms:
    worst15goterms_1.append(goterm+"_"+str(1))
real_go_info_mod_worst = real_go_info[real_go_info.GO_term.isin(worst15goterms_1)]
real_go_info_mod_worst.GO_term = real_go_info_mod_worst.GO_term.str.replace("_1","")

worst15goterms_auc = GO_terms_auc_svm_df.sort_values(by=["auc"], ascending=True)[0:15].reset_index()
worst15goterms_auc.columns=["GO_term","auc","levels","parents"]

worst15goterms_auc.merge(real_go_info_mod_worst[real_go_info_mod_worst["GO_term"].isin(worst15goterms)], on="GO_term")

	GO_term	auc	levels	parents	Name	layer_number
0	GO:0000077	0.284021	1	3	Dna damage checkpoint signaling (1)	1.0
1	GO:0006869	0.299648	3	2	Lipid transport (1)	3.0
2	GO:0051302	0.314545	1	2	Regulation of cell division (1)	1.0
3	GO:0016485	0.318636	3	5	Protein processing (1)	3.0
4	GO:0019722	0.322272	2	1	Calcium-mediated signaling (1)	2.0
5	GO:0046854	0.326276	1	2	Phosphatidylinositol phosphate biosynthetic process (1)	1.0
6	GO:0060740	0.331825	1	6	Prostate gland epithelium morphogenesis (1)	1.0
7	GO:0060444	0.347273	1	8	Branching involved in mammary gland duct morphogenesis (1)	1.0
8	GO:0006919	0.352725	1	3	Activation of cysteine-type endopeptidase activity involved in apoptotic process (1)	1.0
9	GO:0032436	0.353421	1	14	Positive regulation of proteasomal ubiquitin-dependent protein catabolic process (1)	1.0
10	GO:0055119	0.353947	1	1	Relaxation of cardiac muscle (1)	1.0
11	GO:0001892	0.355979	1	5	Embryonic placenta development (1)	1.0
12	GO:0031295	0.364518	0	8	T cell costimulation (1)	0.0
13	GO:0046620	0.365476	1	3	Regulation of organ growth (1)	1.0
14	GO:0008361	0.367423	2	1	Regulation of cell size (1)	2.0

AUPR histogram

GO_terms_aupr_svm_df = pd.DataFrame(list(GO_terms_aupr_svm.items()),columns = ['goterm','aupr']).set_index("goterm")
GO_terms_aupr_svm_df = GO_terms_aupr_svm_df.dropna()
GO_terms_aupr_svm_df.sort_values(by=["aupr"], ascending=False).head()

	aupr
goterm
GO:0036289	0.996209
GO:0006807	0.945077
GO:0050896	0.921869
GO:0043170	0.909722
GO:0009058	0.900903

# Add number of parents
number_parents = {}
levels = {}
for i in range(0,len(GO_terms_aupr_svm_df.index)):
    term = GO_terms_aupr_svm_df.index[i]
    number_parents[GO_terms_aupr_svm_df.index[i]]=len([source for source, _ in  dG.in_edges(term)])
    levels[GO_terms_aupr_svm_df.index[i]]=level_number[term]-1
levels = pd.DataFrame.from_dict(levels, orient='index')
number_parents = pd.DataFrame.from_dict(number_parents, orient='index')

GO_terms_aupr_svm_df = pd.concat([GO_terms_aupr_svm_df, levels,number_parents], axis=1)
GO_terms_aupr_svm_df.columns = ["aupr","levels","parents"]

c = ['#E8384F', '#FD817D', '#FDAE33',
         '#EECC16', '#A4C61A', '#37A862',"#208EA3","#3B6EAB"]

df = px.data.tips()
fig = px.box(GO_terms_aupr_svm_df, x="levels", y="aupr",
             color="levels",
            color_discrete_sequence=c,
             width =600,
             height=400,
              template="simple_white",
              labels=dict(levels="Level of GO hierarchy", aupr="AUPR")
            )
fig.update_traces(width=0.9)

fig.add_shape( # add a horizontal "target" line
    type="line", line_color="salmon", line_width=3, opacity=1, line_dash="dot",
    x0=0, x1=1, xref="paper", y0=0.7, y1=0.7, yref="y"
)


fig.update_layout(
   title=dict(text="<b> AUPR value grouped by level of GO hierarchy <b>",
             x=0.5,
             y=0.9,
              font=dict(size=18),
              xanchor='center',
              yanchor='top'),
    xaxis=dict(ticks="", showticklabels=False, showgrid=False, zeroline=False),
    yaxis=dict(ticks="", showticklabels=True, showgrid=True, zeroline=False),
 #   yaxis_range=[min(yy.flatten()),max(yy.flatten())],
  #  xaxis_range=[min(xx.flatten()),max(xx.flatten())],
    legend=dict(x=1.1, y=1, orientation="v",font=dict(size=11)),
    paper_bgcolor='rgba(0,0,0,0)',
    font=dict(family='Roboto',color= "#36382E",size=15)
    )

fig.show()
pio.write_image(fig, resultsdir+"AUPR_levels.png", width=600, height=400,scale=8)

Example prediction

def f2(goterm):    
    return goterm

combobox_go = interactive(f2, goterm=widgets.Combobox(options=list(GO_terms_auc_svm_df.sort_values(by=["auc"], ascending=False).index)))

Choose drug to study…

display(combobox_go)

selected_go = combobox_go.result

#auc
plt.rcParams['figure.figsize'] = (4, 2)
fpr, tpr, _ = metrics.roc_curve(slim_matrix_single_neuron.loc[selected_go],  platt_matrix.loc[selected_go])
auc = metrics.roc_auc_score(slim_matrix_single_neuron.loc[selected_go],  platt_matrix.loc[selected_go])
plt.plot(fpr,tpr,label="data 1, auc="+str(auc))
plt.legend(loc=4)
plt.show()

plot = pd.concat([pd.DataFrame(slim_matrix_single_neuron.loc[selected_go]),pd.DataFrame(platt_matrix.loc[selected_go])], axis=1)
plot.columns = ["slim","probability"]
ax = sns.boxplot(x="slim", y="probability", data=plot,showfliers=False )

#auc 
fpr, tpr, _ = metrics.roc_curve(slim_matrix_single_neuron.loc[selected_go],  delta_logits_matrix.loc[selected_go])
auc = metrics.roc_auc_score(slim_matrix_single_neuron.loc[selected_go],  delta_logits_matrix.loc[selected_go])
plt.plot(fpr,tpr,label="data 1, auc="+str(auc))
plt.legend(loc=4)
plt.show()

plot = pd.concat([pd.DataFrame(slim_matrix_single_neuron.loc[selected_go]),pd.DataFrame(delta_logits_matrix.loc[selected_go])], axis=1)
plot.columns = ["slim","probability"]
ax = sns.boxplot(x="slim", y="probability", data=plot,showfliers=False )

plt.rcParams['figure.figsize'] = (2, 2)
metrics.ConfusionMatrixDisplay.from_predictions(slim_matrix_single_neuron.loc[selected_go], preds_svm_matrix.loc[selected_go])
plt.grid(visible=None)

print("Accuracy:",metrics.accuracy_score(slim_matrix_single_neuron.loc[selected_go], preds_svm_matrix.loc[selected_go]))
print("Precision:",metrics.precision_score(slim_matrix_single_neuron.loc[selected_go], preds_svm_matrix.loc[selected_go]))
print("Recall:",metrics.recall_score(slim_matrix_single_neuron.loc[selected_go], preds_svm_matrix.loc[selected_go])) #TP / (TP+FN)
print("AUC with score:",auc) #TP / (TP+FN)

Accuracy: 0.9782608695652174
Precision: 0.7894736842105263
Recall: 0.9375
AUC with score: 0.9947429906542057

TN - FP

FN - TP

plt.rcParams['figure.figsize'] = (4, 2)
precision, recall, thresholds = metrics.precision_recall_curve(slim_matrix_single_neuron.loc[selected_go],  preds_svm_matrix.loc[selected_go])
auc_precision_recall = metrics.auc(recall, precision)
plt.plot(recall, precision,label=str(auc_precision_recall))
plt.legend(loc=4)
plt.show()

METRICS drugs

auc_drugs = {}
aupr_drugs = {}
precision_drugs = {}
for drug in list(slim_matrix_single_neuron.columns):
    if slim_matrix_single_neuron.loc[:,drug].sum() ==0:
        continue
    #fpr, tpr, _ = metrics.roc_curve(slim_matrix_single_neuron.loc[:,drug], logits_matrix.loc[:,drug])
    #auc_drugs[drug]  = metrics.auc(fpr, tpr)
    auc_drugs[drug] = metrics.roc_auc_score(slim_matrix_single_neuron.loc[:,drug],  platt_matrix.loc[:,drug])
    precision, recall, thresholds = metrics.precision_recall_curve(slim_matrix_single_neuron.loc[:,drug],  platt_matrix.loc[:,drug])
    aupr_drugs[drug] = metrics.auc(recall, precision)
    precision_drugs[drug] = metrics.precision_score(slim_matrix_single_neuron.loc[:,drug],  preds_svm_matrix.loc[:,drug])

auc_drugs_df = pd.DataFrame(list(auc_drugs.items()),columns = ['goterm','auc']).set_index("goterm")
auc_drugs_df = auc_drugs_df.dropna()

aupr_drugs_df = pd.DataFrame(list(aupr_drugs.items()),columns = ['goterm','aupr']).set_index("goterm")
aupr_drugs_df = aupr_drugs_df.dropna()

precision_drugs_df = pd.DataFrame(list(precision_drugs.items()),columns = ['goterm','precision']).set_index("goterm")
precision_drugs_df = precision_drugs_df.dropna()

AUC histogram drugs

sns.set(rc={'figure.figsize':(10,6)})
fig, ax = plt.subplots()
perc = str(round((100*len(auc_drugs_df[auc_drugs_df["auc"]>0.7])/len(auc_drugs_df)),2))+"%"
N, bins, patches = plt.hist(auc_drugs_df, color=CB_color_cycle[6],bins=50, linewidth=0.1)

for i in range(0,len(bins)-1):
    if bins[i]>0.7:
        patches[i].set_facecolor(CB_color_cycle[5])

plt.yticks(fontsize=16)
plt.xticks(fontsize=16)

ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)
ax.spines['left'].set_visible(False)
ax.spines['bottom'].set_color('#DDDDDD')

# Second, remove the ticks as well.
ax.tick_params(bottom=False, left=True)

# Third, add a horizontal grid (but keep the vertical grid hidden).
# Color the lines a light gray as well.
ax.set_axisbelow(True)
ax.yaxis.grid(True, color='#EEEEEE')
ax.xaxis.grid(False)

plt.xlabel("AUC value", fontsize=20)
plt.ylabel("Number of drugs", fontsize=20)
colors2 = {'Drugs with AUC>=0.7':CB_color_cycle[5]}  
labels = list(colors2.keys())
handles = [plt.Rectangle((0,0),1,1, color=colors2[label]) for label in labels]
plt.legend(handles, labels,fontsize=20, loc="lower left", bbox_to_anchor=(0.35,-0.35))
plt.text(0.79, 6, str(perc), fontsize=20,color='#333333')
plt.title("Overall performance by drugs using mutations", fontsize=24)
# con el que mejor funciona es con la suma normal del attribution 
fig.tight_layout()
fig.savefig(resultsdir+'drugsAUC.png', transparent=True)

AUC waterfall plot drugs

auc_drugs_df =auc_drugs_df.sort_values(by=["auc"], ascending=False)

plt.rcParams['figure.figsize'] = (12, 9)
drugs = auc_drugs_df.index
rhos = auc_drugs_df["auc"]

percentage = round((sum(rhos>0.69)/len(rhos))*100,1)

fig, ax = plt.subplots()
#colors = ['#208EA3' if (x < 0.5) else '#A4C61A' for x in rhos ]
colors = ['#C9C9C9' if (x < 0.69) else "#B678BE" for x in rhos ]
ax.bar(
    x=drugs,
    height=rhos,
    edgecolor=colors,
    linewidth=3
)
plt.xticks([])
plt.yticks(fontsize=28)


# First, let's remove the top, right and left spines (figure borders)
# which really aren't necessary for a bar chart.
# Also, make the bottom spine gray instead of black.
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)
ax.spines['left'].set_visible(False)
ax.spines['bottom'].set_visible(False)
#ax.spines['bottom'].set_color('#DDDDDD')

# Second, remove the ticks as well.
ax.tick_params(bottom=False, left=False)

# Third, add a horizontal grid (but keep the vertical grid hidden).
# Color the lines a light gray as well.
ax.set_axisbelow(False)
ax.yaxis.grid(False)
#ax.yaxis.grid(True, color='#EEEEEE')
ax.xaxis.grid(False)


# Add labels and a title. Note the use of `labelpad` and `pad` to add some
# extra space between the text and the tick labels.
ax.set_xlabel('Drugs', labelpad=-30, color='#333333',fontsize=50)
ax.set_ylabel('AUC-ROC value', labelpad=15, color='#333333',fontsize=50)
ax.set_title('', color='#333333',
             weight='bold')

colors2 = {'High confidence drugs (r>0.5)':'#A4C61A'}  
labels = list(colors2.keys())
handles = [plt.Rectangle((0,0),1,1, color=colors2[label]) for label in labels]
#plt.legend(handles, labels,fontsize=40, loc="lower left",bbox_to_anchor=(0, -0.215))
plt.text(77, 0.32, str(percentage)+"%", fontsize=60,color='#000000')

plt.ylim((-0.1,1.1))
# Make the chart fill out the figure better.
fig.tight_layout()
fig.savefig(resultsdir+'WaterfallModelsSVM_drugs.png', transparent=True)

AUPR histogram drugs

sns.set(rc={'figure.figsize':(5,3)})
perc = str(round((100*len(aupr_drugs_df[aupr_drugs_df["aupr"]>0.69])/len(aupr_drugs_df)),2))+"%"
N, bins, patches = plt.hist(aupr_drugs_df, color=CB_color_cycle[6],bins=50, linewidth=0.1)
for i in range(0,len(bins)-1):
    if bins[i]>0.69:
        patches[i].set_facecolor(CB_color_cycle[3])

plt.xlabel("AUPR drugs", fontsize=16)  
plt.title(perc, fontsize=16)

Text(0.5, 1.0, '33.62%')

Example drug prediction

def f(drug):    
    
    return drug

predictions_nodes = []
for goterm in list(platt_matrix.index):
    predictions_nodes.append(goterm+"_"+str(1))

# add names to go terms
real_go_info_svm= real_go_info[real_go_info.GO_term.isin(predictions_nodes)]
real_go_info_svm.GO_term = real_go_info_svm.GO_term.str.replace("_1","")

combobox = interactive(f, drug=widgets.Combobox(options=list(precision_drugs_df.sort_values(by=["precision"], ascending=False).index)))

Choose drug to study…

display(combobox)

selected_drug_name = combobox.result

sns.set(rc={'figure.figsize':(4,2)})
#auc
fpr, tpr, _ = metrics.roc_curve(slim_matrix_single_neuron.loc[:,selected_drug_name], platt_matrix.loc[:,selected_drug_name] )
auc = metrics.roc_auc_score(slim_matrix_single_neuron.loc[:,selected_drug_name],  platt_matrix.loc[:,selected_drug_name])
plt.plot(fpr,tpr,label="data 1, auc="+str(auc))
plt.legend(loc=4)
plt.show()

plot = pd.concat([pd.DataFrame(slim_matrix_single_neuron.loc[:,selected_drug_name]),pd.DataFrame(platt_matrix.loc[:,selected_drug_name])], axis=1)
plot.columns = ["slim","svm score"]
ax = sns.boxplot(x="slim", y="svm score", data=plot,showfliers=False )

plot = pd.concat([pd.DataFrame(slim_matrix.loc[:,selected_drug_name]),pd.DataFrame(attribution_data_annotated.loc[:,selected_drug_name]*1e4)], axis=1)
plot.columns = ["slim","attribution"]
ax = sns.boxplot(x="slim", y="attribution", data=plot,showfliers=True )

metrics.ConfusionMatrixDisplay.from_predictions(slim_matrix_single_neuron.loc[:,selected_drug_name].round(), preds_svm_matrix.loc[:,selected_drug_name])

<sklearn.metrics._plot.confusion_matrix.ConfusionMatrixDisplay at 0x2502863c8b0>

print("Accuracy:",metrics.accuracy_score(slim_matrix_single_neuron.loc[:,selected_drug_name], preds_svm_matrix.loc[:,selected_drug_name]))
print("Precision:",metrics.precision_score(slim_matrix_single_neuron.loc[:,selected_drug_name], preds_svm_matrix.loc[:,selected_drug_name]))
print("Recall:",metrics.recall_score(slim_matrix_single_neuron.loc[:,selected_drug_name], preds_svm_matrix.loc[:,selected_drug_name])) #TP / (TP+FN)
print("AUC with score:",auc) 

Accuracy: 0.663471778487753
Precision: 0.8651026392961877
Recall: 0.5221238938053098
AUC with score: 0.9947429906542057

# LOS LOGITS DE TEST!!
train_drug_logs = pd.DataFrame(delta_logits_matrix.loc[:,selected_drug_name]).reset_index()
train_drug_logs.columns  = ["GO_term","probability"]
train_drug_logs = train_drug_logs.merge(real_go_info_svm, on="GO_term")
train_drug_logs.sort_values(by=["probability"], ascending=False)

	GO_term	probability	Name	layer_number
578	GO:2000379	2.770126	Positive regulation of reactive oxygen species metabolic process (1)	1.0
253	GO:0043552	2.707570	Positive regulation of phosphatidylinositol 3-kinase activity (1)	0.0
80	GO:0010575	2.282492	Positive regulation of vascular endothelial growth factor production (1)	0.0
633	GO:0051301	2.245231	Cell division (1)	2.0
224	GO:0046777	2.053782	Protein autophosphorylation (1)	1.0
423	GO:1902533	2.014408	Positive regulation of intracellular signal transduction (1)	2.0
458	GO:0035025	1.952270	Positive regulation of rho protein signal transduction (1)	0.0
848	GO:0071670	1.887644	Smooth muscle cell chemotaxis (1)	0.0
348	GO:0006939	1.842256	Smooth muscle contraction (1)	2.0
98	GO:0001932	1.809520	Regulation of protein phosphorylation (1)	4.0
350	GO:0045987	1.783402	Positive regulation of smooth muscle contraction (1)	1.0
45	GO:0001501	1.682999	Skeletal system development (1)	4.0
908	GO:0051899	1.675960	Membrane depolarization (1)	2.0
653	GO:0072593	1.650121	Reactive oxygen species metabolic process (1)	3.0
115	GO:0060312	1.625762	Regulation of blood vessel remodeling (1)	0.0
926	GO:0060020	1.614859	Bergmann glial cell differentiation (1)	0.0
923	GO:0048170	1.598558	Positive regulation of long-term neuronal synaptic plasticity (1)	0.0
99	GO:0001934	1.593723	Positive regulation of protein phosphorylation (1)	3.0
853	GO:0038083	1.588712	Peptidyl-tyrosine autophosphorylation (1)	0.0
713	GO:0035726	1.577983	Common myeloid progenitor cell proliferation (1)	0.0
445	GO:0048008	1.552362	Platelet-derived growth factor receptor signaling pathway (1)	1.0
857	GO:0035584	1.496390	Calcium-mediated signaling using intracellular calcium source (1)	0.0
333	GO:1904019	1.481165	Epithelial cell apoptotic process (1)	1.0
933	GO:0051150	1.474264	Regulation of smooth muscle cell differentiation (1)	1.0
352	GO:0014827	1.453480	Intestine smooth muscle contraction (1)	0.0
218	GO:0006468	1.436484	Protein phosphorylation (1)	5.0
814	GO:0090037	1.416277	Positive regulation of protein kinase c signaling (1)	0.0
894	GO:0048017	1.399588	Inositol lipid-mediated signaling (1)	1.0
506	GO:0007286	1.376021	Spermatid development (1)	1.0
742	GO:0035733	1.371582	Hepatic stellate cell activation (1)	0.0
10	GO:0051403	1.369506	Stress-activated mapk cascade (1)	2.0
702	GO:0048146	1.349525	Positive regulation of fibroblast proliferation (1)	0.0
782	GO:1902042	1.347889	Negative regulation of extrinsic apoptotic signaling pathway via death domain receptors (1)	0.0
8	GO:0000165	1.328354	Mapk cascade (1)	3.0
531	GO:0007585	1.321161	Respiratory gaseous exchange by respiratory system (1)	1.0
492	GO:1905065	1.288165	Positive regulation of vascular associated smooth muscle cell differentiation (1)	0.0
181	GO:0006139	1.261437	Nucleobase-containing compound metabolic process (1)	6.0
670	GO:0031274	1.250440	Positive regulation of pseudopodium assembly (1)	0.0
424	GO:0030513	1.215934	Positive regulation of bmp signaling pathway (1)	0.0
12	GO:0070374	1.209229	Positive regulation of erk1 and erk2 cascade (1)	0.0
593	GO:0050865	1.191004	Regulation of cell activation (1)	5.0
562	GO:0050896	1.177718	Response to stimulus (1)	7.0
24	GO:0007346	1.156784	Regulation of mitotic cell cycle (1)	3.0
640	GO:0071310	1.131852	Cellular response to organic substance (1)	4.0
159	GO:0002548	1.126395	Monocyte chemotaxis (1)	1.0
142	GO:0002443	1.101635	Leukocyte mediated immunity (1)	4.0
141	GO:0050900	1.098856	Leukocyte migration (1)	3.0
583	GO:0032967	1.096638	Positive regulation of collagen biosynthetic process (1)	0.0
49	GO:0001569	1.083831	Branching involved in blood vessel morphogenesis (1)	0.0
437	GO:0007169	1.082604	Transmembrane receptor protein tyrosine kinase signaling pathway (1)	3.0
723	GO:0010921	1.079534	Regulation of phosphatase activity (1)	2.0
105	GO:0045860	1.071511	Positive regulation of protein kinase activity (1)	2.0
421	GO:0045747	1.070015	Positive regulation of notch signaling pathway (1)	0.0
39	GO:0008360	1.064064	Regulation of cell shape (1)	0.0
444	GO:0038084	1.058233	Vascular endothelial growth factor signaling pathway (1)	1.0
833	GO:0010467	1.038215	Gene expression (1)	5.0
365	GO:0090141	1.033165	Positive regulation of mitochondrial fission (1)	0.0
439	GO:0030509	1.027813	Bmp signaling pathway (1)	1.0
553	GO:0034394	1.017983	Protein localization to cell surface (1)	1.0
60	GO:0072210	1.009552	Metanephric nephron development (1)	1.0
427	GO:0046427	1.007946	Positive regulation of receptor signaling pathway via jak-stat (1)	1.0
684	GO:0051770	1.005599	Positive regulation of nitric-oxide synthase biosynthetic process (1)	0.0
309	GO:0034765	1.001361	Regulation of ion transmembrane transport (1)	4.0
655	GO:0008210	0.998843	Estrogen metabolic process (1)	1.0
486	GO:0048484	0.961996	Enteric nervous system development (1)	0.0
809	GO:0014068	0.961267	Positive regulation of phosphatidylinositol 3-kinase signaling (1)	0.0
441	GO:0007259	0.949624	Receptor signaling pathway via jak-stat (1)	2.0
825	GO:0036120	0.941171	Cellular response to platelet-derived growth factor stimulus (1)	0.0
667	GO:0035234	0.934130	Ectopic germ cell programmed cell death (1)	0.0
23	GO:0000278	0.933767	Mitotic cell cycle (1)	4.0
632	GO:1900006	0.924525	Positive regulation of dendrite development (1)	0.0
397	GO:0033627	0.910092	Cell adhesion mediated by integrin (1)	2.0
764	GO:0048701	0.908694	Embryonic cranial skeleton morphogenesis (1)	1.0
624	GO:0010628	0.896611	Positive regulation of gene expression (1)	3.0
862	GO:0035162	0.872366	Embryonic hemopoiesis (1)	1.0
11	GO:0043406	0.860510	Positive regulation of map kinase activity (1)	1.0
74	GO:0001817	0.857088	Regulation of cytokine production (1)	3.0
743	GO:0050918	0.840184	Positive chemotaxis (1)	1.0
829	GO:0010212	0.825924	Response to ionizing radiation (1)	1.0
922	GO:0036324	0.825686	Vascular endothelial growth factor receptor-2 signaling pathway (1)	0.0
895	GO:0070528	0.820011	Protein kinase c signaling (1)	1.0
664	GO:0051092	0.813750	Positive regulation of nf-kappab transcription factor activity (1)	0.0
27	GO:0045840	0.800332	Positive regulation of mitotic nuclear division (1)	1.0
827	GO:0010038	0.794352	Response to metal ion (1)	2.0
592	GO:0045595	0.785394	Regulation of cell differentiation (1)	4.0
263	GO:0010559	0.783904	Regulation of glycoprotein biosynthetic process (1)	1.0
503	GO:0021953	0.781212	Central nervous system neuron differentiation (1)	2.0
674	GO:0071276	0.780750	Cellular response to cadmium ion (1)	0.0
659	GO:0048469	0.780345	Cell maturation (1)	2.0
652	GO:0042180	0.773541	Cellular ketone metabolic process (1)	3.0
44	GO:0048812	0.771740	Neuron projection morphogenesis (1)	3.0
605	GO:0051901	0.770926	Positive regulation of mitochondrial depolarization (1)	0.0
155	GO:0030097	0.758070	Hemopoiesis (1)	4.0
306	GO:0043270	0.753238	Positive regulation of ion transport (1)	3.0
456	GO:0046578	0.747317	Regulation of ras protein signal transduction (1)	2.0
766	GO:0051145	0.741094	Smooth muscle cell differentiation (1)	2.0
379	GO:0032956	0.736770	Regulation of actin cytoskeleton organization (1)	3.0
898	GO:0035924	0.730231	Cellular response to vascular endothelial growth factor stimulus (1)	2.0
897	GO:0035767	0.729807	Endothelial cell chemotaxis (1)	1.0
817	GO:0010033	0.726109	Response to organic substance (1)	5.0
519	GO:0048839	0.725562	Inner ear development (1)	2.0
378	GO:0031532	0.722138	Actin cytoskeleton reorganization (1)	1.0
106	GO:0071900	0.721523	Regulation of protein serine/threonine kinase activity (1)	2.0
544	GO:0060179	0.712624	Male mating behavior (1)	0.0
763	GO:0060325	0.697674	Face morphogenesis (1)	0.0
277	GO:0016925	0.695177	Protein sumoylation (1)	1.0
328	GO:0043065	0.690749	Positive regulation of apoptotic process (1)	2.0
701	GO:0002053	0.689985	Positive regulation of mesenchymal cell proliferation (1)	0.0
77	GO:0002718	0.688320	Regulation of cytokine production involved in immune response (1)	2.0
691	GO:0043542	0.680928	Endothelial cell migration (1)	3.0
280	GO:0006810	0.677814	Transport (1)	7.0
239	GO:0006576	0.673930	Cellular biogenic amine metabolic process (1)	2.0
858	GO:0035019	0.669360	Somatic stem cell population maintenance (1)	1.0
347	GO:0006937	0.665317	Regulation of muscle contraction (1)	2.0
681	GO:2001257	0.650114	Regulation of cation channel activity (1)	2.0
711	GO:0019752	0.649156	Carboxylic acid metabolic process (1)	4.0
716	GO:0070662	0.644697	Mast cell proliferation (1)	0.0
509	GO:0060384	0.639217	Innervation (1)	1.0
900	GO:0042060	0.629958	Wound healing (1)	4.0
401	GO:0010811	0.627079	Positive regulation of cell-substrate adhesion (1)	1.0
388	GO:0051726	0.624874	Regulation of cell cycle (1)	5.0
144	GO:0031295	0.621763	T cell costimulation (1)	0.0
841	GO:0032355	0.617237	Response to estradiol (1)	1.0
126	GO:0002318	0.612203	Myeloid progenitor cell differentiation (1)	0.0
754	GO:0009888	0.609334	Tissue development (1)	4.0
430	GO:0019221	0.607804	Cytokine-mediated signaling pathway (1)	2.0
97	GO:0043129	0.607469	Surfactant homeostasis (1)	0.0
793	GO:0009725	0.604125	Response to hormone (1)	4.0
147	GO:0030218	0.603194	Erythrocyte differentiation (1)	1.0
675	GO:0071277	0.602376	Cellular response to calcium ion (1)	0.0
806	GO:0051056	0.599956	Regulation of small gtpase mediated signal transduction (1)	3.0
46	GO:0060348	0.599483	Bone development (1)	3.0
837	GO:0043536	0.595296	Positive regulation of blood vessel endothelial cell migration (1)	1.0
863	GO:0035855	0.595221	Megakaryocyte development (1)	0.0
803	GO:0042475	0.592086	Odontogenesis of dentin-containing tooth (1)	2.0
66	GO:0001824	0.588798	Blastocyst development (1)	1.0
495	GO:0060976	0.586013	Coronary vasculature development (1)	1.0
838	GO:0038033	0.585984	Positive regulation of endothelial cell chemotaxis by vegf-activated vascular endothelial growth factor receptor signaling pathway (1)	0.0
626	GO:0051649	0.585010	Establishment of localization in cell (1)	4.0
899	GO:0035994	0.581520	Response to muscle stretch (1)	1.0
398	GO:0045785	0.575910	Positive regulation of cell adhesion (1)	3.0
471	GO:0060045	0.574196	Positive regulation of cardiac muscle cell proliferation (1)	0.0
617	GO:0008354	0.569914	Germ cell migration (1)	0.0
331	GO:0071887	0.563795	Leukocyte apoptotic process (1)	2.0
508	GO:0042552	0.562630	Myelination (1)	2.0
47	GO:0048704	0.560470	Embryonic skeletal system morphogenesis (1)	2.0
386	GO:0007049	0.553817	Cell cycle (1)	6.0
346	GO:0006936	0.550409	Muscle contraction (1)	3.0
225	GO:0006470	0.541583	Protein dephosphorylation (1)	3.0
750	GO:0044281	0.539816	Small molecule metabolic process (1)	5.0
835	GO:0016239	0.538943	Positive regulation of macroautophagy (1)	1.0
219	GO:0006975	0.532966	Dna damage induced protein phosphorylation (1)	0.0
573	GO:0010629	0.530721	Negative regulation of gene expression (1)	3.0
354	GO:0050728	0.528698	Negative regulation of inflammatory response (1)	2.0
746	GO:0033327	0.520751	Leydig cell differentiation (1)	0.0
802	GO:0060766	0.520552	Negative regulation of androgen receptor signaling pathway (1)	0.0
249	GO:0019216	0.518909	Regulation of lipid metabolic process (1)	3.0
231	GO:0033619	0.516921	Membrane protein proteolysis (1)	1.0
428	GO:0007219	0.510598	Notch signaling pathway (1)	1.0
906	GO:0043549	0.506907	Regulation of kinase activity (1)	3.0
59	GO:0035788	0.505476	Cell migration involved in metanephros development (1)	0.0
708	GO:0050890	0.505448	Cognition (1)	2.0
468	GO:1903010	0.502791	Regulation of bone development (1)	0.0
912	GO:0043534	0.496543	Blood vessel endothelial cell migration (1)	2.0
148	GO:0050852	0.496154	T cell receptor signaling pathway (1)	1.0
639	GO:0060326	0.490465	Cell chemotaxis (1)	2.0
317	GO:0006897	0.488535	Endocytosis (1)	3.0
465	GO:0007275	0.485383	Multicellular organism development (1)	7.0
772	GO:0060485	0.484666	Mesenchyme development (1)	3.0
823	GO:0045471	0.483879	Response to ethanol (1)	1.0
373	GO:0030838	0.479914	Positive regulation of actin filament polymerization (1)	0.0
160	GO:0002573	0.478546	Myeloid leukocyte differentiation (1)	3.0
877	GO:0060437	0.473475	Lung growth (1)	0.0
245	GO:0006629	0.469312	Lipid metabolic process (1)	5.0
114	GO:0051894	0.466675	Positive regulation of focal adhesion assembly (1)	0.0
406	GO:0048041	0.466386	Focal adhesion assembly (1)	1.0
932	GO:0097021	0.465441	Lymphocyte migration into lymphoid organs (1)	0.0
339	GO:2000352	0.461676	Negative regulation of endothelial cell apoptotic process (1)	0.0
874	GO:1903053	0.452737	Regulation of extracellular matrix organization (1)	1.0
284	GO:0051050	0.451125	Positive regulation of transport (1)	4.0
13	GO:0046330	0.444601	Positive regulation of jnk cascade (1)	0.0
256	GO:0046474	0.443735	Glycerophospholipid biosynthetic process (1)	2.0
588	GO:0019222	0.443139	Regulation of metabolic process (1)	7.0
459	GO:0007267	0.428833	Cell-cell signaling (1)	5.0
919	GO:0046677	0.427086	Response to antibiotic (1)	1.0
462	GO:0007268	0.426575	Chemical synaptic transmission (1)	4.0
706	GO:0043547	0.426347	Positive regulation of gtpase activity (1)	1.0
660	GO:0045347	0.425159	Negative regulation of mhc class ii biosynthetic process (1)	0.0
290	GO:2000300	0.421019	Regulation of synaptic vesicle exocytosis (1)	1.0
791	GO:0009582	0.420489	Detection of abiotic stimulus (1)	2.0
907	GO:0051881	0.420291	Regulation of mitochondrial membrane potential (1)	1.0
517	GO:0043586	0.419816	Tongue development (1)	1.0
533	GO:0030168	0.419395	Platelet activation (1)	2.0
469	GO:0060173	0.411322	Limb development (1)	1.0
90	GO:0072284	0.410934	Metanephric s-shaped body morphogenesis (1)	0.0
780	GO:0046890	0.404557	Regulation of lipid biosynthetic process (1)	2.0
229	GO:0016485	0.400777	Protein processing (1)	3.0
446	GO:0048010	0.399575	Vascular endothelial growth factor receptor signaling pathway (1)	1.0
402	GO:0022407	0.398607	Regulation of cell-cell adhesion (1)	3.0
287	GO:0099111	0.397633	Microtubule-based transport (1)	3.0
194	GO:0006355	0.390046	Regulation of transcription, dna-templated (1)	4.0
913	GO:0090630	0.382248	Activation of gtpase activity (1)	0.0
122	GO:0002062	0.381242	Chondrocyte differentiation (1)	2.0
629	GO:0051174	0.380683	Regulation of phosphorus metabolic process (1)	6.0
668	GO:0010976	0.374728	Positive regulation of neuron projection development (1)	1.0
604	GO:0045088	0.374664	Regulation of innate immune response (1)	2.0
139	GO:0002684	0.374517	Positive regulation of immune system process (1)	4.0
250	GO:0044255	0.373685	Cellular lipid metabolic process (1)	4.0
163	GO:0002685	0.368480	Regulation of leukocyte migration (1)	2.0
369	GO:0055003	0.366810	Cardiac myofibril assembly (1)	0.0
265	GO:0051247	0.362984	Positive regulation of protein metabolic process (1)	4.0
795	GO:0043627	0.362212	Response to estrogen (1)	1.0
707	GO:0007202	0.359908	Activation of phospholipase c activity (1)	0.0
223	GO:0018108	0.359532	Peptidyl-tyrosine phosphorylation (1)	3.0
832	GO:0042220	0.359499	Response to cocaine (1)	1.0
715	GO:0061351	0.358465	Neural precursor cell proliferation (1)	3.0
873	GO:0002327	0.358081	Immature b cell differentiation (1)	0.0
16	GO:0046329	0.357586	Negative regulation of jnk cascade (1)	1.0
409	GO:0007166	0.352431	Cell surface receptor signaling pathway (1)	4.0
753	GO:1901135	0.352161	Carbohydrate derivative metabolic process (1)	4.0
69	GO:0001755	0.350614	Neural crest cell migration (1)	1.0
440	GO:0030512	0.350318	Negative regulation of transforming growth factor beta receptor signaling pathway (1)	0.0
563	GO:1900272	0.349758	Negative regulation of long-term synaptic potentiation (1)	0.0
650	GO:0034329	0.348915	Cell junction assembly (1)	2.0
230	GO:0030162	0.336130	Regulation of proteolysis (1)	3.0
175	GO:0005975	0.330773	Carbohydrate metabolic process (1)	4.0
627	GO:0035306	0.328011	Positive regulation of dephosphorylation (1)	1.0
400	GO:0007160	0.326200	Cell-matrix adhesion (1)	2.0
455	GO:0016601	0.324410	Rac protein signal transduction (1)	2.0
697	GO:0050678	0.322499	Regulation of epithelial cell proliferation (1)	3.0
71	GO:0060444	0.322093	Branching involved in mammary gland duct morphogenesis (1)	1.0
226	GO:0035304	0.320405	Regulation of protein dephosphorylation (1)	2.0
412	GO:0009966	0.306725	Regulation of signal transduction (1)	5.0
914	GO:0046486	0.298756	Glycerolipid metabolic process (1)	3.0
539	GO:0050795	0.293322	Regulation of behavior (1)	2.0
86	GO:0072006	0.288499	Nephron development (1)	2.0
337	GO:0043525	0.284469	Positive regulation of neuron apoptotic process (1)	0.0
625	GO:0051902	0.284041	Negative regulation of mitochondrial depolarization (1)	0.0
58	GO:0003338	0.282674	Metanephros morphogenesis (1)	1.0
811	GO:0043124	0.281702	Negative regulation of i-kappab kinase/nf-kappab signaling (1)	0.0
812	GO:0051897	0.280267	Positive regulation of protein kinase b signaling (1)	0.0
203	GO:0006163	0.279176	Purine nucleotide metabolic process (1)	3.0
543	GO:0007612	0.277571	Learning (1)	1.0
466	GO:0007389	0.275989	Pattern specification process (1)	3.0
883	GO:0032148	0.273937	Activation of protein kinase b activity (1)	0.0
483	GO:0035909	0.270466	Aorta morphogenesis (1)	1.0
755	GO:0016358	0.270034	Dendrite development (1)	3.0
307	GO:0034766	0.269283	Negative regulation of ion transmembrane transport (1)	1.0
513	GO:0030900	0.265273	Forebrain development (1)	3.0
479	GO:0048598	0.253519	Embryonic morphogenesis (1)	4.0
507	GO:0007416	0.252929	Synapse assembly (1)	1.0
860	GO:0051928	0.247690	Positive regulation of calcium ion transport (1)	2.0
651	GO:0050808	0.247245	Synapse organization (1)	3.0
890	GO:0071353	0.244414	Cellular response to interleukin-4 (1)	1.0
392	GO:0032467	0.243007	Positive regulation of cytokinesis (1)	0.0
695	GO:0015980	0.237863	Energy derivation by oxidation of organic compounds (1)	3.0
235	GO:0032436	0.237590	Positive regulation of proteasomal ubiquitin-dependent protein catabolic process (1)	1.0
560	GO:0043473	0.231280	Pigmentation (1)	2.0
463	GO:0035249	0.230532	Synaptic transmission, glutamatergic (1)	1.0
870	GO:0070527	0.229018	Platelet aggregation (1)	1.0
273	GO:0016575	0.227418	Histone deacetylation (1)	2.0
32	GO:0000422	0.224098	Autophagy of mitochondrion (1)	2.0
113	GO:0001952	0.223395	Regulation of cell-matrix adhesion (1)	1.0
9	GO:0043408	0.223296	Regulation of mapk cascade (1)	2.0
125	GO:0002244	0.223128	Hematopoietic progenitor cell differentiation (1)	2.0
132	GO:0002274	0.221454	Myeloid leukocyte activation (1)	2.0
869	GO:0030318	0.209787	Melanocyte differentiation (1)	1.0
0	GO:0000077	0.209594	Dna damage checkpoint signaling (1)	1.0
255	GO:0006644	0.209513	Phospholipid metabolic process (1)	3.0
645	GO:0071300	0.209465	Cellular response to retinoic acid (1)	0.0
729	GO:0120035	0.207325	Regulation of plasma membrane bounded cell projection organization (1)	3.0
796	GO:0097067	0.207250	Cellular response to thyroid hormone stimulus (1)	0.0
516	GO:0007423	0.206232	Sensory organ development (1)	3.0
410	GO:0007186	0.205939	G protein-coupled receptor signaling pathway (1)	3.0
722	GO:0042325	0.203618	Regulation of phosphorylation (1)	5.0
794	GO:0043434	0.202441	Response to peptide hormone (1)	3.0
88	GO:0090184	0.201141	Positive regulation of kidney development (1)	0.0
431	GO:0031663	0.200051	Lipopolysaccharide-mediated signaling pathway (1)	1.0
866	GO:0030101	0.198593	Natural killer cell activation (1)	2.0
38	GO:0000902	0.193896	Cell morphogenesis (1)	4.0
259	GO:0009259	0.192137	Ribonucleotide metabolic process (1)	3.0
703	GO:0048661	0.191886	Positive regulation of smooth muscle cell proliferation (1)	1.0
740	GO:0014911	0.191054	Positive regulation of smooth muscle cell migration (1)	1.0
714	GO:0050673	0.189629	Epithelial cell proliferation (1)	4.0
43	GO:0050770	0.188075	Regulation of axonogenesis (1)	2.0
381	GO:0008064	0.187642	Regulation of actin polymerization or depolymerization (1)	2.0
851	GO:0070933	0.185342	Histone h4 deacetylation (1)	0.0
762	GO:0060749	0.181899	Mammary gland alveolus development (1)	0.0
454	GO:0007266	0.181338	Rho protein signal transduction (1)	1.0
541	GO:0008542	0.180964	Visual learning (1)	0.0
499	GO:1990384	0.180877	Hyaloid vascular plexus regression (1)	0.0
320	GO:0006914	0.178279	Autophagy (1)	4.0
42	GO:0048675	0.176485	Axon extension (1)	2.0
234	GO:0010952	0.174912	Positive regulation of peptidase activity (1)	2.0
192	GO:0006352	0.168084	Dna-templated transcription, initiation (1)	3.0
448	GO:0008277	0.168080	Regulation of g protein-coupled receptor signaling pathway (1)	2.0
582	GO:1902459	0.162029	Positive regulation of stem cell population maintenance (1)	0.0
489	GO:0021766	0.161871	Hippocampus development (1)	1.0
154	GO:0050778	0.157385	Positive regulation of immune response (1)	3.0
187	GO:0071897	0.156799	Dna biosynthetic process (1)	2.0
7	GO:0000122	0.155105	Negative regulation of transcription by rna polymerase ii (1)	1.0
821	GO:0034097	0.153698	Response to cytokine (1)	3.0
124	GO:0002218	0.151919	Activation of innate immune response (1)	1.0
699	GO:0033689	0.151375	Negative regulation of osteoblast proliferation (1)	0.0
288	GO:0032940	0.151138	Secretion by cell (1)	5.0
854	GO:0070102	0.145028	Interleukin-6-mediated signaling pathway (1)	0.0
361	GO:0010638	0.143294	Positive regulation of organelle organization (1)	2.0
612	GO:0019827	0.141470	Stem cell population maintenance (1)	2.0
781	GO:0008625	0.139268	Extrinsic apoptotic signaling pathway via death domain receptors (1)	1.0
101	GO:0033141	0.136334	Positive regulation of peptidyl-serine phosphorylation of stat protein (1)	0.0
611	GO:1902904	0.136088	Negative regulation of supramolecular fiber organization (1)	2.0
643	GO:0071222	0.135913	Cellular response to lipopolysaccharide (1)	2.0
394	GO:0007059	0.133987	Chromosome segregation (1)	3.0
824	GO:0071363	0.126406	Cellular response to growth factor stimulus (1)	3.0
53	GO:0001570	0.126375	Vasculogenesis (1)	1.0
738	GO:0098586	0.123247	Cellular response to virus (1)	1.0
472	GO:0001553	0.119373	Luteinization (1)	0.0
109	GO:1905564	0.116462	Positive regulation of vascular endothelial cell proliferation (1)	0.0
709	GO:0019233	0.115463	Sensory perception of pain (1)	1.0
728	GO:0030032	0.113460	Lamellipodium assembly (1)	1.0
257	GO:0046488	0.111935	Phosphatidylinositol metabolic process (1)	2.0
313	GO:0051281	0.111192	Positive regulation of release of sequestered calcium ion into cytosol (1)	1.0
924	GO:0035754	0.107144	B cell chemotaxis (1)	0.0
658	GO:0048468	0.103878	Cell development (1)	5.0
545	GO:0008016	0.102922	Regulation of heart contraction (1)	3.0
532	GO:0007596	0.102694	Blood coagulation (1)	3.0
103	GO:0042531	0.102081	Positive regulation of tyrosine phosphorylation of stat protein (1)	0.0
938	GO:0007158	0.100508	Neuron cell-cell adhesion (1)	0.0
383	GO:0051497	0.100321	Negative regulation of stress fiber assembly (1)	0.0
57	GO:0001656	0.100188	Metanephros development (1)	2.0
83	GO:0002720	0.098565	Positive regulation of cytokine production involved in immune response (1)	1.0
382	GO:0030041	0.097715	Actin filament polymerization (1)	2.0
89	GO:0072239	0.093313	Metanephric glomerulus vasculature development (1)	0.0
180	GO:0019318	0.092513	Hexose metabolic process (1)	2.0
555	GO:1903078	0.092013	Positive regulation of protein localization to plasma membrane (1)	1.0
434	GO:0048011	0.091817	Neurotrophin trk receptor signaling pathway (1)	1.0
119	GO:0060740	0.091714	Prostate gland epithelium morphogenesis (1)	1.0
95	GO:0001894	0.091179	Tissue homeostasis (1)	2.0
661	GO:0046326	0.090707	Positive regulation of glucose import (1)	0.0
435	GO:0016055	0.090703	Wnt signaling pathway (1)	2.0
613	GO:0032922	0.089808	Circadian regulation of gene expression (1)	0.0
450	GO:0051209	0.087976	Release of sequestered calcium ion into cytosol (1)	3.0
477	GO:0040016	0.085668	Embryonic cleavage (1)	0.0
607	GO:0042391	0.085377	Regulation of membrane potential (1)	3.0
669	GO:0010592	0.084513	Positive regulation of lamellipodium assembly (1)	0.0
170	GO:0003007	0.084095	Heart morphogenesis (1)	3.0
269	GO:0031397	0.081637	Negative regulation of protein ubiquitination (1)	1.0
206	GO:0006298	0.080826	Mismatch repair (1)	0.0
31	GO:0070301	0.080430	Cellular response to hydrogen peroxide (1)	1.0
130	GO:0002819	0.080102	Regulation of adaptive immune response (1)	3.0
29	GO:1901031	0.077813	Regulation of response to reactive oxygen species (1)	1.0
242	GO:0090314	0.077607	Positive regulation of protein targeting to membrane (1)	0.0
417	GO:0060395	0.076956	Smad protein signal transduction (1)	1.0
710	GO:0055119	0.076428	Relaxation of cardiac muscle (1)	1.0
567	GO:0051641	0.073979	Cellular localization (1)	5.0
491	GO:0060440	0.069181	Trachea formation (1)	0.0
608	GO:0043114	0.069090	Regulation of vascular permeability (1)	1.0
190	GO:0045739	0.068981	Positive regulation of dna repair (1)	1.0
283	GO:0051049	0.068824	Regulation of transport (1)	5.0
595	GO:0051302	0.067812	Regulation of cell division (1)	1.0
91	GO:0001837	0.067510	Epithelial to mesenchymal transition (1)	2.0
110	GO:0001942	0.066958	Hair follicle development (1)	1.0
275	GO:0090042	0.066526	Tubulin deacetylation (1)	1.0
41	GO:0007411	0.065935	Axon guidance (1)	2.0
679	GO:0042310	0.063952	Vasoconstriction (1)	1.0
232	GO:0010951	0.062732	Negative regulation of endopeptidase activity (1)	2.0
865	GO:0030217	0.062144	T cell differentiation (1)	3.0
171	GO:0003014	0.057983	Renal system process (1)	2.0
501	GO:0007507	0.057228	Heart development (1)	4.0
70	GO:0001763	0.054372	Morphogenesis of a branching structure (1)	2.0
351	GO:0060048	0.052464	Cardiac muscle contraction (1)	2.0
121	GO:0090050	0.049572	Positive regulation of cell migration involved in sprouting angiogenesis (1)	0.0
169	GO:0002764	0.049060	Immune response-regulating signaling pathway (1)	3.0
630	GO:2000377	0.047289	Regulation of reactive oxygen species metabolic process (1)	2.0
537	GO:0007626	0.045891	Locomotory behavior (1)	2.0
799	GO:0009743	0.045252	Response to carbohydrate (1)	2.0
301	GO:0032388	0.044514	Positive regulation of intracellular transport (1)	1.0
40	GO:0034446	0.043394	Substrate adhesion-dependent cell spreading (1)	1.0
152	GO:0045087	0.042899	Innate immune response (1)	3.0
73	GO:0001779	0.041596	Natural killer cell differentiation (1)	1.0
212	GO:0051090	0.040406	Regulation of dna-binding transcription factor activity (1)	2.0
864	GO:0030183	0.038386	B cell differentiation (1)	1.0
705	GO:0051353	0.036453	Positive regulation of oxidoreductase activity (1)	1.0
587	GO:0050921	0.036116	Positive regulation of chemotaxis (1)	1.0
760	GO:0048286	0.035821	Lung alveolus development (1)	1.0
254	GO:0006687	0.035424	Glycosphingolipid metabolic process (1)	2.0
228	GO:0006508	0.033855	Proteolysis (1)	4.0
757	GO:0021987	0.030030	Cerebral cortex development (1)	2.0
673	GO:0043392	0.029313	Negative regulation of dna binding (1)	1.0
530	GO:0007584	0.028301	Response to nutrient (1)	3.0
712	GO:0033002	0.028034	Muscle cell proliferation (1)	2.0
792	GO:0060560	0.027744	Developmental growth involved in morphogenesis (1)	3.0
797	GO:0071383	0.026769	Cellular response to steroid hormone stimulus (1)	2.0
920	GO:0036092	0.025989	Phosphatidylinositol-3-phosphate biosynthetic process (1)	0.0
396	GO:0007162	0.024820	Negative regulation of cell adhesion (1)	2.0
498	GO:0061029	0.024413	Eyelid development in camera-type eye (1)	0.0
480	GO:0048565	0.023576	Digestive tract development (1)	1.0
51	GO:0045766	0.022903	Positive regulation of angiogenesis (1)	1.0
574	GO:0008285	0.020185	Negative regulation of cell population proliferation (1)	3.0
521	GO:0035051	0.019783	Cardiocyte differentiation (1)	2.0
205	GO:0045740	0.019424	Positive regulation of dna replication (1)	1.0
487	GO:0030325	0.018166	Adrenal gland development (1)	0.0
601	GO:0034103	0.018123	Regulation of tissue remodeling (1)	1.0
261	GO:0051171	0.014388	Regulation of nitrogen compound metabolic process (1)	6.0
570	GO:0045597	0.014362	Positive regulation of cell differentiation (1)	3.0
842	GO:0071407	0.014361	Cellular response to organic cyclic compound (1)	3.0
936	GO:0051000	0.014216	Positive regulation of nitric-oxide synthase activity (1)	0.0
461	GO:0050804	0.011722	Modulation of chemical synaptic transmission (1)	3.0
54	GO:2001214	0.010912	Positive regulation of vasculogenesis (1)	0.0
236	GO:0043161	0.009887	Proteasome-mediated ubiquitin-dependent protein catabolic process (1)	2.0
734	GO:0051702	0.006784	Biological process involved in interaction with symbiont (1)	2.0
717	GO:0046651	0.006589	Lymphocyte proliferation (1)	2.0
323	GO:0016236	0.006518	Macroautophagy (1)	3.0
158	GO:0002862	0.006214	Negative regulation of inflammatory response to antigenic stimulus (1)	1.0
619	GO:0050790	0.006102	Regulation of catalytic activity (1)	4.0
520	GO:0007498	0.005849	Mesoderm development (1)	3.0
136	GO:0002376	0.005563	Immune system process (1)	6.0
631	GO:0050920	0.005385	Regulation of chemotaxis (1)	2.0
403	GO:0033628	0.003111	Regulation of cell adhesion mediated by integrin (1)	1.0
345	GO:0006919	0.001149	Activation of cysteine-type endopeptidase activity involved in apoptotic process (1)	1.0
730	GO:0031175	0.000000	Neuron projection development (1)	4.0
304	GO:0046942	-0.001338	Carboxylic acid transport (1)	3.0
474	GO:0030539	-0.001885	Male genitalia development (1)	0.0
561	GO:0048511	-0.003138	Rhythmic process (1)	3.0
736	GO:0009617	-0.003666	Response to bacterium (1)	3.0
529	GO:0007568	-0.004377	Aging (1)	1.0
747	GO:0048878	-0.006747	Chemical homeostasis (1)	6.0
291	GO:0030072	-0.007065	Peptide hormone secretion (1)	3.0
580	GO:0045907	-0.009718	Positive regulation of vasoconstriction (1)	0.0
467	GO:0009791	-0.011347	Post-embryonic development (1)	1.0
935	GO:0048103	-0.011384	Somatic stem cell division (1)	0.0
657	GO:0045165	-0.012040	Cell fate commitment (1)	3.0
414	GO:0023019	-0.016733	Signal transduction involved in regulation of gene expression (1)	0.0
429	GO:0007229	-0.017112	Integrin-mediated signaling pathway (1)	1.0
312	GO:1904062	-0.018714	Regulation of cation transmembrane transport (1)	3.0
296	GO:0015031	-0.019362	Protein transport (1)	4.0
191	GO:0045944	-0.020718	Positive regulation of transcription by rna polymerase ii (1)	2.0
602	GO:0046620	-0.020955	Regulation of organ growth (1)	1.0
247	GO:0008610	-0.024022	Lipid biosynthetic process (1)	3.0
576	GO:0050866	-0.024773	Negative regulation of cell activation (1)	2.0
868	GO:0048863	-0.027968	Stem cell differentiation (1)	2.0
310	GO:0051924	-0.028544	Regulation of calcium ion transport (1)	3.0
332	GO:0097190	-0.028734	Apoptotic signaling pathway (1)	4.0
482	GO:0048557	-0.029065	Embryonic digestive tract morphogenesis (1)	0.0
262	GO:0045429	-0.029754	Positive regulation of nitric oxide biosynthetic process (1)	0.0
622	GO:0043086	-0.032086	Negative regulation of catalytic activity (1)	3.0
623	GO:0031334	-0.034770	Positive regulation of protein-containing complex assembly (1)	2.0
131	GO:0002821	-0.037160	Positive regulation of adaptive immune response (1)	2.0
618	GO:0032409	-0.037577	Regulation of transporter activity (1)	3.0
63	GO:0001666	-0.040150	Response to hypoxia (1)	2.0
196	GO:0006357	-0.041500	Regulation of transcription by rna polymerase ii (1)	3.0
270	GO:0031056	-0.041705	Regulation of histone modification (1)	2.0
733	GO:0030335	-0.043802	Positive regulation of cell migration (1)	3.0
93	GO:0001843	-0.044624	Neural tube closure (1)	1.0
370	GO:0033044	-0.044682	Regulation of chromosome organization (1)	2.0
408	GO:0007165	-0.044905	Signal transduction (1)	6.0
153	GO:0050776	-0.045236	Regulation of immune response (1)	4.0
227	GO:0032516	-0.046939	Positive regulation of phosphoprotein phosphatase activity (1)	0.0
217	GO:0006457	-0.046986	Protein folding (1)	1.0
415	GO:0030522	-0.048782	Intracellular receptor signaling pathway (1)	2.0
366	GO:0090201	-0.049666	Negative regulation of release of cytochrome c from mitochondria (1)	0.0
436	GO:0060079	-0.050457	Excitatory postsynaptic potential (1)	1.0
380	GO:0051017	-0.052351	Actin filament bundle assembly (1)	1.0
903	GO:0050863	-0.053759	Regulation of t cell activation (1)	3.0
78	GO:0032760	-0.054179	Positive regulation of tumor necrosis factor production (1)	0.0
188	GO:0009165	-0.055647	Nucleotide biosynthetic process (1)	3.0
904	GO:0042113	-0.058054	B cell activation (1)	3.0
138	GO:0002683	-0.058846	Negative regulation of immune system process (1)	3.0
826	GO:0071364	-0.059153	Cellular response to epidermal growth factor stimulus (1)	0.0
915	GO:0050872	-0.059361	White fat cell differentiation (1)	0.0
102	GO:0050731	-0.063114	Positive regulation of peptidyl-tyrosine phosphorylation (1)	2.0
133	GO:0043303	-0.063260	Mast cell degranulation (1)	1.0
494	GO:0060840	-0.069316	Artery development (1)	2.0
504	GO:0048709	-0.071150	Oligodendrocyte differentiation (1)	2.0
178	GO:0005984	-0.071330	Disaccharide metabolic process (1)	0.0
737	GO:0051607	-0.071636	Defense response to virus (1)	2.0
732	GO:0060997	-0.074427	Dendritic spine morphogenesis (1)	1.0
460	GO:0023061	-0.075653	Signal release (1)	4.0
67	GO:0001892	-0.076334	Embryonic placenta development (1)	1.0
724	GO:0036473	-0.088337	Cell death in response to oxidative stress (1)	2.0
447	GO:0007173	-0.090517	Epidermal growth factor receptor signaling pathway (1)	2.0
353	GO:0006954	-0.092872	Inflammatory response (1)	3.0
861	GO:0090280	-0.094645	Positive regulation of calcium ion import (1)	0.0
731	GO:0031529	-0.095254	Ruffle organization (1)	1.0
779	GO:0008544	-0.096671	Epidermis development (1)	3.0
901	GO:0042110	-0.098950	T cell activation (1)	4.0
690	GO:2001020	-0.101079	Regulation of response to dna damage stimulus (1)	2.0
360	GO:0007030	-0.102202	Golgi organization (1)	1.0
295	GO:0051047	-0.107145	Positive regulation of secretion (1)	3.0
786	GO:0034605	-0.107349	Cellular response to heat (1)	1.0
749	GO:0009058	-0.108343	Biosynthetic process (1)	5.0
688	GO:1900407	-0.109537	Regulation of cellular response to oxidative stress (1)	2.0
735	GO:0046718	-0.110283	Viral entry into host cell (1)	1.0
76	GO:0001819	-0.110409	Positive regulation of cytokine production (1)	2.0
50	GO:0002040	-0.110656	Sprouting angiogenesis (1)	1.0
692	GO:0010595	-0.112175	Positive regulation of endothelial cell migration (1)	2.0
419	GO:0003376	-0.112243	Sphingosine-1-phosphate receptor signaling pathway (1)	0.0
374	GO:2000251	-0.113035	Positive regulation of actin cytoskeleton reorganization (1)	0.0
845	GO:0016071	-0.114794	Mrna metabolic process (1)	4.0
589	GO:0042752	-0.116589	Regulation of circadian rhythm (1)	2.0
615	GO:0035265	-0.117147	Organ growth (1)	2.0
918	GO:0046854	-0.117793	Phosphatidylinositol phosphate biosynthetic process (1)	1.0
485	GO:0007422	-0.118904	Peripheral nervous system development (1)	2.0
81	GO:0032729	-0.121441	Positive regulation of interferon-gamma production (1)	0.0
591	GO:0010941	-0.121750	Regulation of cell death (1)	5.0
759	GO:0032835	-0.121813	Glomerulus development (1)	1.0
511	GO:0030182	-0.123468	Neuron differentiation (1)	5.0
260	GO:0006807	-0.123894	Nitrogen compound metabolic process (1)	7.0
859	GO:0021782	-0.127920	Glial cell development (1)	2.0
108	GO:0001938	-0.130000	Positive regulation of endothelial cell proliferation (1)	1.0
335	GO:2000270	-0.130342	Negative regulation of fibroblast apoptotic process (1)	0.0
162	GO:0060374	-0.130465	Mast cell differentiation (1)	0.0
87	GO:0072073	-0.132456	Kidney epithelium development (1)	2.0
183	GO:0006401	-0.132593	Rna catabolic process (1)	3.0
818	GO:0010243	-0.134405	Response to organonitrogen compound (1)	4.0
641	GO:0071417	-0.135033	Cellular response to organonitrogen compound (1)	3.0
464	GO:0060291	-0.136241	Long-term synaptic potentiation (1)	1.0
929	GO:0051341	-0.137416	Regulation of oxidoreductase activity (1)	2.0
581	GO:0120162	-0.138251	Positive regulation of cold-induced thermogenesis (1)	0.0
389	GO:0010564	-0.140360	Regulation of cell cycle process (1)	4.0
443	GO:0035860	-0.140553	Glial cell-derived neurotrophic factor receptor signaling pathway (1)	0.0
20	GO:0070507	-0.141310	Regulation of microtubule cytoskeleton organization (1)	2.0
453	GO:0007265	-0.142317	Ras protein signal transduction (1)	3.0
751	GO:0046034	-0.143417	Atp metabolic process (1)	2.0
3	GO:1900087	-0.145967	Positive regulation of g1/s transition of mitotic cell cycle (1)	0.0
214	GO:0006412	-0.146506	Translation (1)	4.0
566	GO:0032879	-0.149430	Regulation of localization (1)	6.0
671	GO:0032092	-0.152370	Positive regulation of protein binding (1)	1.0
761	GO:0060021	-0.155229	Roof of mouth development (1)	1.0
420	GO:2001241	-0.155496	Positive regulation of extrinsic apoptotic signaling pathway in absence of ligand (1)	0.0
405	GO:0007159	-0.155632	Leukocyte cell-cell adhesion (1)	3.0
358	GO:0007005	-0.155655	Mitochondrion organization (1)	3.0
210	GO:1902275	-0.156027	Regulation of chromatin organization (1)	1.0
311	GO:0030001	-0.158264	Metal ion transport (1)	5.0
810	GO:0043123	-0.158702	Positive regulation of i-kappab kinase/nf-kappab signaling (1)	0.0
168	GO:0045580	-0.161790	Regulation of t cell differentiation (1)	2.0
72	GO:0001764	-0.163226	Neuron migration (1)	1.0
776	GO:0060644	-0.163884	Mammary gland epithelial cell differentiation (1)	0.0
319	GO:0006909	-0.166043	Phagocytosis (1)	2.0
268	GO:0016570	-0.169677	Histone modification (1)	4.0
788	GO:0009410	-0.171927	Response to xenobiotic stimulus (1)	2.0
128	GO:1902036	-0.173697	Regulation of hematopoietic stem cell differentiation (1)	0.0
609	GO:0048167	-0.175411	Regulation of synaptic plasticity (1)	2.0
377	GO:0031032	-0.181549	Actomyosin structure organization (1)	2.0
438	GO:0007179	-0.182780	Transforming growth factor beta receptor signaling pathway (1)	1.0
28	GO:0000302	-0.183602	Response to reactive oxygen species (1)	2.0
745	GO:0009653	-0.188122	Anatomical structure morphogenesis (1)	5.0
395	GO:0007155	-0.188355	Cell adhesion (1)	5.0
535	GO:0050910	-0.188639	Detection of mechanical stimulus involved in sensory perception of sound (1)	0.0
14	GO:0043407	-0.189998	Negative regulation of map kinase activity (1)	1.0
636	GO:0030048	-0.190360	Actin filament-based movement (1)	2.0
909	GO:0042593	-0.191255	Glucose homeostasis (1)	2.0
546	GO:0008104	-0.192695	Protein localization (1)	5.0
289	GO:0007269	-0.196526	Neurotransmitter secretion (1)	2.0
885	GO:1900180	-0.200364	Regulation of protein localization to nucleus (1)	1.0
30	GO:1901300	-0.200519	Positive regulation of hydrogen peroxide-mediated programmed cell death (1)	0.0
739	GO:1902903	-0.203430	Regulation of supramolecular fiber organization (1)	3.0
847	GO:0045055	-0.204997	Regulated exocytosis (1)	2.0
299	GO:0030705	-0.206607	Cytoskeleton-dependent intracellular transport (1)	3.0
340	GO:2001234	-0.207987	Negative regulation of apoptotic signaling pathway (1)	3.0
849	GO:0043966	-0.208541	Histone h3 acetylation (1)	2.0
286	GO:0055085	-0.210703	Transmembrane transport (1)	6.0
363	GO:0051494	-0.211867	Negative regulation of cytoskeleton organization (1)	2.0
48	GO:0001525	-0.211963	Angiogenesis (1)	2.0
813	GO:0051898	-0.215146	Negative regulation of protein kinase b signaling (1)	0.0
700	GO:0033690	-0.223856	Positive regulation of osteoblast proliferation (1)	0.0
209	GO:0006338	-0.224254	Chromatin remodeling (1)	2.0
416	GO:0035556	-0.225162	Intracellular signal transduction (1)	4.0
916	GO:2000739	-0.225462	Regulation of mesenchymal stem cell differentiation (1)	0.0
79	GO:0032740	-0.225949	Positive regulation of interleukin-17 production (1)	0.0
572	GO:0034767	-0.226631	Positive regulation of ion transmembrane transport (1)	2.0
272	GO:0031398	-0.229217	Positive regulation of protein ubiquitination (1)	2.0
222	GO:0018107	-0.231930	Peptidyl-threonine phosphorylation (1)	1.0
879	GO:0031103	-0.232786	Axon regeneration (1)	1.0
413	GO:0009968	-0.233227	Negative regulation of signal transduction (1)	4.0
765	GO:0021795	-0.237208	Cerebral cortex cell migration (1)	1.0
325	GO:0006915	-0.240649	Apoptotic process (1)	5.0
172	GO:0003158	-0.242769	Endothelium development (1)	2.0
357	GO:0006997	-0.247765	Nucleus organization (1)	2.0
725	GO:0070997	-0.248013	Neuron death (1)	2.0
355	GO:0050729	-0.250210	Positive regulation of inflammatory response (1)	1.0
233	GO:0016579	-0.250907	Protein deubiquitination (1)	1.0
666	GO:0010727	-0.258854	Negative regulation of hydrogen peroxide metabolic process (1)	0.0
202	GO:0006753	-0.259533	Nucleoside phosphate metabolic process (1)	4.0
685	GO:0051973	-0.259761	Positive regulation of telomerase activity (1)	0.0
549	GO:0009306	-0.261559	Protein secretion (1)	3.0
778	GO:0045793	-0.270168	Positive regulation of cell size (1)	0.0
303	GO:1904659	-0.270188	Glucose transmembrane transport (1)	1.0
676	GO:0030282	-0.272104	Bone mineralization (1)	1.0
294	GO:0051046	-0.276779	Regulation of secretion (1)	4.0
362	GO:0033043	-0.280077	Regulation of organelle organization (1)	4.0
123	GO:0002064	-0.285938	Epithelial cell development (1)	2.0
282	GO:0016192	-0.287866	Vesicle-mediated transport (1)	4.0
678	GO:0071333	-0.289435	Cellular response to glucose stimulus (1)	1.0
523	GO:0007517	-0.293992	Muscle organ development (1)	3.0
150	GO:0002437	-0.297868	Inflammatory response to antigenic stimulus (1)	2.0
704	GO:1904707	-0.299166	Positive regulation of vascular associated smooth muscle cell proliferation (1)	0.0
771	GO:0031016	-0.299979	Pancreas development (1)	2.0
937	GO:0051640	-0.307828	Organelle localization (1)	3.0
107	GO:1905563	-0.308080	Negative regulation of vascular endothelial cell proliferation (1)	0.0
404	GO:0007156	-0.311359	Homophilic cell adhesion via plasma membrane adhesion molecules (1)	1.0
238	GO:0043162	-0.311445	Ubiquitin-dependent protein catabolic process via the multivesicular body sorting pathway (1)	1.0
752	GO:0043170	-0.315334	Macromolecule metabolic process (1)	7.0
552	GO:0033365	-0.319737	Protein localization to organelle (1)	3.0
881	GO:0031929	-0.320242	Tor signaling (1)	2.0
484	GO:0007399	-0.320323	Nervous system development (1)	6.0
129	GO:0002250	-0.320676	Adaptive immune response (1)	4.0
741	GO:0016477	-0.323694	Cell migration (1)	4.0
600	GO:0010632	-0.324795	Regulation of epithelial cell migration (1)	3.0
197	GO:0006367	-0.325397	Transcription initiation from rna polymerase ii promoter (1)	2.0
118	GO:0060571	-0.325595	Morphogenesis of an epithelial fold (1)	1.0
505	GO:0007283	-0.329296	Spermatogenesis (1)	2.0
542	GO:0048149	-0.329477	Behavioral response to ethanol (1)	0.0
391	GO:0090068	-0.333050	Positive regulation of cell cycle process (1)	2.0
656	GO:0030154	-0.339581	Cell differentiation (1)	6.0
698	GO:0070663	-0.341786	Regulation of leukocyte proliferation (1)	2.0
164	GO:0051249	-0.342420	Regulation of lymphocyte activation (1)	4.0
720	GO:0051261	-0.344762	Protein depolymerization (1)	2.0
475	GO:0050769	-0.344990	Positive regulation of neurogenesis (1)	2.0
165	GO:0050870	-0.345649	Positive regulation of t cell activation (1)	2.0
432	GO:0038007	-0.346961	Netrin-activated signaling pathway (1)	0.0
246	GO:0008202	-0.348429	Steroid metabolic process (1)	3.0
831	GO:0001975	-0.357673	Response to amphetamine (1)	0.0
177	GO:0045821	-0.361584	Positive regulation of glycolytic process (1)	0.0
127	GO:0002320	-0.363702	Lymphoid progenitor cell differentiation (1)	1.0
399	GO:0098609	-0.364601	Cell-cell adhesion (1)	4.0
599	GO:0017157	-0.372042	Regulation of exocytosis (1)	2.0
790	GO:0034644	-0.372186	Cellular response to uv (1)	1.0
568	GO:0008284	-0.372632	Positive regulation of cell population proliferation (1)	2.0
75	GO:0001818	-0.372931	Negative regulation of cytokine production (1)	1.0
610	GO:0031333	-0.373027	Negative regulation of protein-containing complex assembly (1)	2.0
770	GO:0009887	-0.378818	Animal organ morphogenesis (1)	4.0
18	GO:0000226	-0.382412	Microtubule cytoskeleton organization (1)	3.0
244	GO:0042307	-0.383034	Positive regulation of protein import into nucleus (1)	0.0
510	GO:0042063	-0.386958	Gliogenesis (1)	3.0
252	GO:0046889	-0.389004	Positive regulation of lipid biosynthetic process (1)	1.0
683	GO:0048477	-0.389075	Oogenesis (1)	1.0
686	GO:0097009	-0.390741	Energy homeostasis (1)	0.0
597	GO:0060627	-0.391978	Regulation of vesicle-mediated transport (1)	3.0
594	GO:0051128	-0.392248	Regulation of cellular component organization (1)	5.0
36	GO:0000723	-0.397902	Telomere maintenance (1)	1.0
579	GO:0040018	-0.399025	Positive regulation of multicellular organism growth (1)	0.0
55	GO:0001649	-0.403752	Osteoblast differentiation (1)	1.0
642	GO:0034599	-0.410954	Cellular response to oxidative stress (1)	3.0
318	GO:0006898	-0.412020	Receptor-mediated endocytosis (1)	2.0
518	GO:0042472	-0.414984	Inner ear morphogenesis (1)	1.0
816	GO:0032008	-0.416975	Positive regulation of tor signaling (1)	1.0
808	GO:1902532	-0.418085	Negative regulation of intracellular signal transduction (1)	3.0
135	GO:0042093	-0.420233	T-helper cell differentiation (1)	1.0
364	GO:0140013	-0.421435	Meiotic nuclear division (1)	2.0
536	GO:0007610	-0.428170	Behavior (1)	3.0
267	GO:0045732	-0.434807	Positive regulation of protein catabolic process (1)	2.0
789	GO:0009416	-0.439464	Response to light stimulus (1)	2.0
637	GO:0030198	-0.439683	Extracellular matrix organization (1)	2.0
82	GO:0032743	-0.458060	Positive regulation of interleukin-2 production (1)	0.0
694	GO:0032869	-0.463421	Cellular response to insulin stimulus (1)	2.0
646	GO:0071320	-0.466282	Cellular response to camp (1)	0.0
146	GO:0043029	-0.470875	T cell homeostasis (1)	1.0
911	GO:0060416	-0.475618	Response to growth hormone (1)	1.0
237	GO:0006511	-0.479298	Ubiquitin-dependent protein catabolic process (1)	3.0
819	GO:0014070	-0.480176	Response to organic cyclic compound (1)	4.0
896	GO:0097193	-0.483526	Intrinsic apoptotic signaling pathway (1)	3.0
134	GO:0002366	-0.488727	Leukocyte activation involved in immune response (1)	3.0
493	GO:0001946	-0.489050	Lymphangiogenesis (1)	0.0
689	GO:1905897	-0.495409	Regulation of response to endoplasmic reticulum stress (1)	2.0
478	GO:0048568	-0.497049	Embryonic organ development (1)	3.0
820	GO:0033993	-0.497561	Response to lipid (1)	3.0
934	GO:0051258	-0.500444	Protein polymerization (1)	3.0
800	GO:0030521	-0.503978	Androgen receptor signaling pathway (1)	1.0
276	GO:0016567	-0.510030	Protein ubiquitination (1)	3.0
663	GO:0050821	-0.512838	Protein stabilization (1)	0.0
768	GO:0051147	-0.515025	Regulation of muscle cell differentiation (1)	2.0
384	GO:0007018	-0.516240	Microtubule-based movement (1)	4.0
200	GO:0006281	-0.520134	Dna repair (1)	2.0
496	GO:0048608	-0.521065	Reproductive structure development (1)	2.0
921	GO:0035790	-0.529398	Platelet-derived growth factor receptor-alpha signaling pathway (1)	0.0
207	GO:0006303	-0.530286	Double-strand break repair via nonhomologous end joining (1)	1.0
548	GO:1903829	-0.534357	Positive regulation of protein localization (1)	3.0
889	GO:0098780	-0.534495	Response to mitochondrial depolarisation (1)	1.0
281	GO:0006811	-0.536119	Ion transport (1)	6.0
336	GO:0043524	-0.548174	Negative regulation of neuron apoptotic process (1)	1.0
184	GO:0006275	-0.549978	Regulation of dna replication (1)	2.0
96	GO:0048873	-0.558233	Homeostasis of number of cells within a tissue (1)	0.0
449	GO:0007204	-0.558363	Positive regulation of cytosolic calcium ion concentration (1)	4.0
744	GO:0055082	-0.561669	Cellular chemical homeostasis (1)	5.0
329	GO:0043066	-0.563158	Negative regulation of apoptotic process (1)	4.0
37	GO:0000724	-0.565085	Double-strand break repair via homologous recombination (1)	1.0
871	GO:0042551	-0.565380	Neuron maturation (1)	1.0
525	GO:0048741	-0.566143	Skeletal muscle fiber development (1)	1.0
557	GO:0072655	-0.572037	Establishment of protein localization to mitochondrion (1)	1.0
215	GO:0006417	-0.572163	Regulation of translation (1)	3.0
584	GO:0040008	-0.572873	Regulation of growth (1)	3.0
748	GO:0009056	-0.572913	Catabolic process (1)	5.0
556	GO:0051223	-0.574651	Regulation of protein transport (1)	3.0
433	GO:0097191	-0.576815	Extrinsic apoptotic signaling pathway (1)	3.0
502	GO:0007420	-0.577438	Brain development (1)	4.0
371	GO:0010821	-0.581599	Regulation of mitochondrion organization (1)	2.0
326	GO:0008637	-0.587399	Apoptotic mitochondrial changes (1)	1.0
767	GO:0051146	-0.588274	Striated muscle cell differentiation (1)	2.0
314	GO:0070588	-0.591082	Calcium ion transmembrane transport (1)	4.0
248	GO:0016042	-0.605006	Lipid catabolic process (1)	2.0
411	GO:0009755	-0.607054	Hormone-mediated signaling pathway (1)	2.0
182	GO:0016070	-0.607882	Rna metabolic process (1)	5.0
888	GO:0034976	-0.613362	Response to endoplasmic reticulum stress (1)	3.0
176	GO:0044262	-0.620829	Cellular carbohydrate metabolic process (1)	3.0
846	GO:0099504	-0.627336	Synaptic vesicle cycle (1)	2.0
528	GO:0007565	-0.627705	Female pregnancy (1)	2.0
211	GO:0031507	-0.627760	Heterochromatin assembly (1)	1.0
94	GO:0001889	-0.633760	Liver development (1)	1.0
52	GO:0001541	-0.634171	Ovarian follicle development (1)	1.0
137	GO:0002682	-0.635094	Regulation of immune system process (1)	5.0
620	GO:0051098	-0.635782	Regulation of binding (1)	3.0
266	GO:0030163	-0.652510	Protein catabolic process (1)	4.0
638	GO:0033554	-0.652740	Cellular response to stress (1)	4.0
777	GO:0050680	-0.661189	Negative regulation of epithelial cell proliferation (1)	2.0
425	GO:0060391	-0.664363	Positive regulation of smad protein signal transduction (1)	0.0
375	GO:0051496	-0.667875	Positive regulation of stress fiber assembly (1)	0.0
85	GO:0001823	-0.670272	Mesonephros development (1)	2.0
654	GO:0090398	-0.671529	Cellular senescence (1)	1.0
774	GO:0030216	-0.675144	Keratinocyte differentiation (1)	2.0
316	GO:0033157	-0.678469	Regulation of intracellular protein transport (1)	1.0
693	GO:1904646	-0.683366	Cellular response to amyloid-beta (1)	0.0
186	GO:2000278	-0.687722	Regulation of dna biosynthetic process (1)	1.0
418	GO:2001240	-0.689139	Negative regulation of extrinsic apoptotic signaling pathway in absence of ligand (1)	0.0
117	GO:0060562	-0.691717	Epithelial tube morphogenesis (1)	2.0
644	GO:0071230	-0.699092	Cellular response to amino acid stimulus (1)	1.0
298	GO:0006886	-0.703192	Intracellular protein transport (1)	3.0
473	GO:0008584	-0.709411	Male gonad development (1)	1.0
687	GO:0072384	-0.726414	Organelle transport along microtubule (1)	2.0
785	GO:0009266	-0.729968	Response to temperature stimulus (1)	2.0
116	GO:0002009	-0.733249	Morphogenesis of an epithelium (1)	3.0
867	GO:0045444	-0.735911	Fat cell differentiation (1)	2.0
564	GO:0045596	-0.736029	Negative regulation of cell differentiation (1)	2.0
804	GO:0030855	-0.743127	Epithelial cell differentiation (1)	3.0
887	GO:0034504	-0.747907	Protein localization to nucleus (1)	2.0
64	GO:0071456	-0.749105	Cellular response to hypoxia (1)	1.0
173	GO:0003300	-0.749363	Cardiac muscle hypertrophy (1)	2.0
422	GO:0046628	-0.749367	Positive regulation of insulin receptor signaling pathway (1)	0.0
783	GO:0008630	-0.759892	Intrinsic apoptotic signaling pathway in response to dna damage (1)	2.0
84	GO:0001822	-0.761027	Kidney development (1)	3.0
208	GO:0006325	-0.765908	Chromatin organization (1)	3.0
349	GO:0055118	-0.766833	Negative regulation of cardiac muscle contraction (1)	0.0
497	GO:0060041	-0.772237	Retina development in camera-type eye (1)	1.0
836	GO:1901987	-0.773018	Regulation of cell cycle phase transition (1)	3.0
850	GO:0070932	-0.775462	Histone h3 deacetylation (1)	0.0
522	GO:0048738	-0.777561	Cardiac muscle tissue development (1)	2.0
26	GO:1901990	-0.788841	Regulation of mitotic cell cycle phase transition (1)	2.0
606	GO:0048638	-0.795928	Regulation of developmental growth (1)	2.0
143	GO:0038096	-0.798475	Fc-gamma receptor signaling pathway involved in phagocytosis (1)	0.0
649	GO:0071478	-0.804830	Cellular response to radiation (1)	2.0
775	GO:0022612	-0.808633	Gland morphogenesis (1)	2.0
92	GO:0010718	-0.808642	Positive regulation of epithelial to mesenchymal transition (1)	1.0
534	GO:0030193	-0.809407	Regulation of blood coagulation (1)	2.0
185	GO:0051054	-0.817126	Positive regulation of dna metabolic process (1)	2.0
930	GO:1902074	-0.824018	Response to salt (1)	1.0
514	GO:0021575	-0.825947	Hindbrain morphogenesis (1)	1.0
876	GO:0046632	-0.839055	Alpha-beta t cell differentiation (1)	2.0
558	GO:0016032	-0.841189	Viral process (1)	3.0
490	GO:0007435	-0.854168	Salivary gland morphogenesis (1)	1.0
359	GO:0007010	-0.858980	Cytoskeleton organization (1)	4.0
718	GO:0008361	-0.861438	Regulation of cell size (1)	2.0
801	GO:0033143	-0.875603	Regulation of intracellular steroid hormone receptor signaling pathway (1)	1.0
179	GO:0006096	-0.888237	Glycolytic process (1)	1.0
157	GO:0048538	-0.899567	Thymus development (1)	0.0
886	GO:0034502	-0.908113	Protein localization to chromosome (1)	2.0
647	GO:0071392	-0.910313	Cellular response to estradiol stimulus (1)	0.0
457	GO:0035022	-0.913306	Positive regulation of rac protein signal transduction (1)	0.0
56	GO:0045668	-0.913637	Negative regulation of osteoblast differentiation (1)	0.0
843	GO:0014823	-0.918185	Response to activity (1)	1.0
376	GO:0007015	-0.919887	Actin filament organization (1)	3.0
166	GO:0030890	-0.921340	Positive regulation of b cell proliferation (1)	0.0
526	GO:0048743	-0.926052	Positive regulation of skeletal muscle fiber development (1)	0.0
21	GO:0051225	-0.929849	Spindle assembly (1)	2.0
596	GO:0060341	-0.932901	Regulation of cellular localization (1)	3.0
140	GO:0045321	-0.933341	Leukocyte activation (1)	5.0
855	GO:1903578	-0.938108	Regulation of atp metabolic process (1)	1.0
100	GO:0033138	-0.947197	Positive regulation of peptidyl-serine phosphorylation (1)	1.0
34	GO:1903146	-0.948778	Regulation of autophagy of mitochondrion (1)	1.0
120	GO:1905278	-0.954451	Positive regulation of epithelial tube formation (1)	0.0
726	GO:0065003	-0.957268	Protein-containing complex assembly (1)	4.0
330	GO:0071839	-0.961212	Apoptotic process in bone marrow cell (1)	0.0
902	GO:0046631	-0.968398	Alpha-beta t cell activation (1)	3.0
621	GO:0032410	-0.978890	Negative regulation of transporter activity (1)	1.0
17	GO:0000209	-0.995522	Protein polyubiquitination (1)	2.0
840	GO:0043154	-0.996503	Negative regulation of cysteine-type endopeptidase activity involved in apoptotic process (1)	1.0
35	GO:0061734	-0.998003	Parkin-mediated stimulation of mitophagy in response to mitochondrial depolarization (1)	0.0
387	GO:0051321	-1.010241	Meiotic cell cycle (1)	3.0
6	GO:0010971	-1.013845	Positive regulation of g2/m transition of mitotic cell cycle (1)	0.0
488	GO:0030878	-1.022587	Thyroid gland development (1)	0.0
598	GO:0043254	-1.024401	Regulation of protein-containing complex assembly (1)	3.0
161	GO:0030316	-1.031163	Osteoclast differentiation (1)	2.0
315	GO:0046902	-1.038293	Regulation of mitochondrial membrane permeability (1)	1.0
758	GO:0031099	-1.044014	Regeneration (1)	2.0
356	GO:0006996	-1.050513	Organelle organization (1)	5.0
547	GO:0032880	-1.061375	Regulation of protein localization (1)	4.0
470	GO:0042733	-1.062045	Embryonic digit morphogenesis (1)	0.0
590	GO:0050792	-1.063199	Regulation of viral process (1)	2.0
875	GO:0033077	-1.072052	T cell differentiation in thymus (1)	1.0
25	GO:0045930	-1.075304	Negative regulation of mitotic cell cycle (1)	2.0
293	GO:0032024	-1.085745	Positive regulation of insulin secretion (1)	1.0
305	GO:0034220	-1.105994	Ion transmembrane transport (1)	5.0
279	GO:0018205	-1.119880	Peptidyl-lysine modification (1)	4.0
300	GO:0032386	-1.120402	Regulation of intracellular transport (1)	2.0
19	GO:0031109	-1.121358	Microtubule polymerization or depolymerization (1)	2.0
302	GO:0006869	-1.132701	Lipid transport (1)	3.0
368	GO:0060271	-1.144707	Cilium assembly (1)	3.0
258	GO:0006694	-1.145934	Steroid biosynthetic process (1)	2.0
571	GO:2000010	-1.155468	Positive regulation of protein localization to cell surface (1)	0.0
880	GO:0031667	-1.156877	Response to nutrient levels (1)	4.0
220	GO:0016572	-1.176296	Histone phosphorylation (1)	1.0
805	GO:0090090	-1.179703	Negative regulation of canonical wnt signaling pathway (1)	0.0
856	GO:0019722	-1.180979	Calcium-mediated signaling (1)	2.0
481	GO:0030324	-1.181819	Lung development (1)	2.0
927	GO:0042632	-1.192404	Cholesterol homeostasis (1)	0.0
334	GO:2000811	-1.206493	Negative regulation of anoikis (1)	0.0
696	GO:0030336	-1.218248	Negative regulation of cell migration (1)	2.0
891	GO:0034405	-1.223979	Response to fluid shear stress (1)	1.0
61	GO:0001658	-1.225087	Branching involved in ureteric bud morphogenesis (1)	1.0
672	GO:0032091	-1.230462	Negative regulation of protein binding (1)	1.0
292	GO:0046883	-1.239220	Regulation of hormone secretion (1)	3.0
585	GO:0048589	-1.242926	Developmental growth (1)	4.0
634	GO:0061024	-1.243050	Membrane organization (1)	2.0
324	GO:0016241	-1.250511	Regulation of macroautophagy (1)	2.0
554	GO:0072659	-1.270281	Protein localization to plasma membrane (1)	2.0
476	GO:0048714	-1.271201	Positive regulation of oligodendrocyte differentiation (1)	0.0
603	GO:0061045	-1.272009	Negative regulation of wound healing (1)	2.0
917	GO:1900020	-1.277862	Positive regulation of protein kinase c activity (1)	0.0
407	GO:0030010	-1.292763	Establishment of cell polarity (1)	1.0
559	GO:0022414	-1.306268	Reproductive process (1)	4.0
199	GO:0006270	-1.310311	Dna replication initiation (1)	1.0
327	GO:0033028	-1.310645	Myeloid cell apoptotic process (1)	1.0
221	GO:0018105	-1.313496	Peptidyl-serine phosphorylation (1)	2.0
882	GO:0032147	-1.314908	Activation of protein kinase activity (1)	1.0
297	GO:0006839	-1.314960	Mitochondrial transport (1)	2.0
773	GO:0060612	-1.316095	Adipose tissue development (1)	1.0
815	GO:1901224	-1.319667	Positive regulation of nik/nf-kappab signaling (1)	0.0
551	GO:1903077	-1.319677	Negative regulation of protein localization to plasma membrane (1)	1.0
149	GO:0050853	-1.320551	B cell receptor signaling pathway (1)	1.0
807	GO:1901796	-1.330292	Regulation of signal transduction by p53 class mediator (1)	1.0
682	GO:0007026	-1.340212	Negative regulation of microtubule depolymerization (1)	0.0
515	GO:0021549	-1.341320	Cerebellum development (1)	2.0
798	GO:0051384	-1.346453	Response to glucocorticoid (1)	1.0
390	GO:0044770	-1.348006	Cell cycle phase transition (1)	4.0
198	GO:0006260	-1.359349	Dna replication (1)	3.0
614	GO:0035264	-1.365256	Multicellular organism growth (1)	1.0
5	GO:0000086	-1.366187	G2/m transition of mitotic cell cycle (1)	1.0
628	GO:0043467	-1.377923	Regulation of generation of precursor metabolites and energy (1)	2.0
616	GO:0001556	-1.391091	Oocyte maturation (1)	0.0
201	GO:0006310	-1.394633	Dna recombination (1)	3.0
243	GO:0006606	-1.399288	Protein import into nucleus (1)	1.0
104	GO:0006469	-1.403847	Negative regulation of protein kinase activity (1)	2.0
784	GO:0042771	-1.409468	Intrinsic apoptotic signaling pathway in response to dna damage by p53 class mediator (1)	1.0
204	GO:0006261	-1.419899	Dna-dependent dna replication (1)	2.0
2	GO:0000082	-1.425082	G1/s transition of mitotic cell cycle (1)	2.0
878	GO:0030593	-1.429383	Neutrophil chemotaxis (1)	1.0
839	GO:0031047	-1.438952	Gene silencing by rna (1)	2.0
15	GO:0070373	-1.439598	Negative regulation of erk1 and erk2 cascade (1)	0.0
367	GO:1901029	-1.442702	Negative regulation of mitochondrial outer membrane permeabilization involved in apoptotic signaling pathway (1)	0.0
385	GO:0060632	-1.444681	Regulation of microtubule-based movement (1)	1.0
285	GO:0051051	-1.447128	Negative regulation of transport (1)	3.0
1	GO:0045737	-1.452510	Positive regulation of cyclin-dependent protein serine/threonine kinase activity (1)	0.0
928	GO:0051453	-1.491236	Regulation of intracellular ph (1)	1.0
569	GO:0030307	-1.507144	Positive regulation of cell growth (1)	2.0
264	GO:0042177	-1.517738	Negative regulation of protein catabolic process (1)	1.0
442	GO:0008286	-1.524273	Insulin receptor signaling pathway (1)	1.0
524	GO:0007519	-1.531881	Skeletal muscle tissue development (1)	2.0
65	GO:0001701	-1.542908	In utero embryonic development (1)	2.0
174	GO:0010613	-1.546047	Positive regulation of cardiac muscle hypertrophy (1)	1.0
167	GO:0045637	-1.553460	Regulation of myeloid cell differentiation (1)	2.0
213	GO:0006396	-1.579762	Rna processing (1)	4.0
925	GO:1990403	-1.599465	Embryonic brain development (1)	0.0
62	GO:0001662	-1.634974	Behavioral fear response (1)	1.0
112	GO:0060789	-1.642170	Hair follicle placode formation (1)	0.0
321	GO:0010507	-1.662573	Negative regulation of autophagy (1)	1.0
193	GO:0006368	-1.663610	Transcription elongation from rna polymerase ii promoter (1)	1.0
910	GO:0051354	-1.665789	Negative regulation of oxidoreductase activity (1)	1.0
648	GO:0071549	-1.672280	Cellular response to dexamethasone stimulus (1)	0.0
240	GO:0006605	-1.701265	Protein targeting (1)	2.0
251	GO:0045833	-1.715199	Negative regulation of lipid metabolic process (1)	2.0
341	GO:2001236	-1.716145	Regulation of extrinsic apoptotic signaling pathway (1)	2.0
322	GO:0010508	-1.734826	Positive regulation of autophagy (1)	2.0
344	GO:1902236	-1.763757	Negative regulation of endoplasmic reticulum stress-induced intrinsic apoptotic signaling pathway (1)	0.0
828	GO:0010039	-1.764349	Response to iron ion (1)	1.0
577	GO:2001021	-1.770162	Negative regulation of response to dna damage stimulus (1)	1.0
342	GO:2001243	-1.793574	Negative regulation of intrinsic apoptotic signaling pathway (1)	2.0
830	GO:0071480	-1.811677	Cellular response to gamma radiation (1)	0.0
241	GO:0006612	-1.832631	Protein targeting to membrane (1)	1.0
550	GO:1904950	-1.845239	Negative regulation of establishment of protein localization (1)	2.0
586	GO:2000773	-1.847992	Negative regulation of cellular senescence (1)	0.0
33	GO:0000423	-1.852021	Mitophagy (1)	1.0
145	GO:0001782	-1.865421	B cell homeostasis (1)	0.0
527	GO:0007528	-1.888030	Neuromuscular junction development (1)	1.0
931	GO:0002931	-1.889223	Response to ischemia (1)	0.0
111	GO:0031069	-1.907723	Hair follicle morphogenesis (1)	0.0
575	GO:0030308	-1.913032	Negative regulation of cell growth (1)	1.0
393	GO:1901988	-1.952405	Negative regulation of cell cycle phase transition (1)	2.0
68	GO:0042659	-1.958074	Regulation of cell fate specification (1)	0.0
834	GO:0035195	-1.964770	Gene silencing by mirna (1)	1.0
271	GO:2000757	-1.982632	Negative regulation of peptidyl-lysine acetylation (1)	1.0
451	GO:0007263	-1.986508	Nitric oxide mediated signal transduction (1)	1.0
677	GO:0010977	-2.012737	Negative regulation of neuron projection development (1)	1.0
822	GO:0046898	-2.020251	Response to cycloheximide (1)	0.0
893	GO:0035094	-2.023491	Response to nicotine (1)	1.0
635	GO:0099173	-2.072765	Postsynapse organization (1)	2.0
884	GO:0032469	-2.081057	Endoplasmic reticulum calcium ion homeostasis (1)	1.0
538	GO:0048266	-2.139693	Behavioral response to pain (1)	0.0
787	GO:0042149	-2.188398	Cellular response to glucose starvation (1)	0.0
756	GO:0021695	-2.195335	Cerebellar cortex development (1)	1.0
662	GO:0031648	-2.195396	Protein destabilization (1)	0.0
727	GO:0070842	-2.214919	Aggresome assembly (1)	0.0
4	GO:2000134	-2.218448	Negative regulation of g1/s transition of mitotic cell cycle (1)	1.0
500	GO:0046666	-2.221412	Retinal cell programmed cell death (1)	0.0
151	GO:0006959	-2.228889	Humoral immune response (1)	2.0
216	GO:0045727	-2.232845	Positive regulation of translation (1)	1.0
274	GO:0034983	-2.241321	Peptidyl-lysine deacetylation (1)	0.0
565	GO:1902455	-2.310039	Negative regulation of stem cell population maintenance (1)	0.0
372	GO:0070584	-2.320318	Mitochondrion morphogenesis (1)	0.0
343	GO:1902166	-2.325709	Negative regulation of intrinsic apoptotic signaling pathway in response to dna damage by p53 class mediator (1)	0.0
512	GO:0008045	-2.344717	Motor neuron axon guidance (1)	1.0
769	GO:0010832	-2.404325	Negative regulation of myotube differentiation (1)	0.0
905	GO:0050864	-2.430784	Regulation of b cell activation (1)	2.0
338	GO:1900118	-2.496567	Negative regulation of execution phase of apoptosis (1)	0.0
426	GO:0090263	-2.498030	Positive regulation of canonical wnt signaling pathway (1)	0.0
540	GO:0007617	-2.520665	Mating behavior (1)	1.0
872	GO:0002326	-2.609504	B cell lineage commitment (1)	0.0
680	GO:0031640	-2.667289	Killing of cells of another organism (1)	1.0
278	GO:0016573	-2.686301	Histone acetylation (1)	3.0
156	GO:0048536	-2.714980	Spleen development (1)	0.0
308	GO:0051926	-2.798095	Negative regulation of calcium ion transport (1)	1.0
721	GO:1905710	-2.815392	Positive regulation of membrane permeability (1)	1.0
665	GO:0045636	-2.820949	Positive regulation of melanocyte differentiation (1)	0.0
719	GO:0043244	-2.878623	Regulation of protein-containing complex disassembly (1)	2.0
195	GO:0006360	-2.938382	Transcription by rna polymerase i (1)	2.0
22	GO:0007098	-3.141939	Centrosome cycle (1)	2.0
892	GO:0070059	-3.411097	Intrinsic apoptotic signaling pathway in response to endoplasmic reticulum stress (1)	1.0
189	GO:1903800	-3.468461	Positive regulation of production of mirnas involved in gene silencing by mirna (1)	0.0
844	GO:0043922	-3.856003	Negative regulation by host of viral transcription (1)	0.0
452	GO:0010750	-3.917943	Positive regulation of nitric oxide mediated signal transduction (1)	0.0
852	GO:0036289	-8.673968	Peptidyl-serine autophosphorylation (1)	0.0

Final model SVM

Once the models have been cross-validated we create the final models using all samples…

GO_terms_auc_svm_final = {}
GO_terms_aupr_svm_final = {}
GO_terms_precision_svm_final = {}
models_svm = {}

# Perform logistics
for goterm in sparseGO_terms:
    #print(goterm)
    goterm_drugs = slim_matrix.loc[[goterm+"_"+str(1)]].values.flatten()
    
    if sum(goterm_drugs) <= 8:
        continue

    list_nodes = []
    for i in range(1,7):
        list_nodes.append(goterm+"_"+str(i))

    score = attribution_data_annotated.loc[list_nodes].T
    score_mod = score.divide(score.std()).fillna(0)
    
    X_train = score_mod
    X_test = score_mod
    y_train = goterm_drugs
    y_test = goterm_drugs
    
    #gamma = 1/(X_train.shape[1]*X_train.to_numpy().var())
    gamma="scale"
    C=1
    
    
        
    svm_model = svm.SVC(C=C,gamma=gamma, kernel='rbf',
                           class_weight="balanced",
                            tol=0.001,
                            probability=True,
                           random_state=1234)
    # fit the model with data
    svm_model.fit(X_train,y_train)
    y_pred=svm_model.predict(X_test)

    #auc
    y_pred_proba = svm_model.predict_proba(X_test)[::,1]  # platt values
    #y_pred_proba = svm_model.decision_function(X_test)
    
    GO_terms_auc_svm_final[goterm] = metrics.roc_auc_score(y_test, y_pred_proba)

    precision, recall, thresholds = metrics.precision_recall_curve(y_test, y_pred_proba)
    GO_terms_aupr_svm_final[goterm] = metrics.auc(recall, precision)
    GO_terms_precision_svm_final[goterm] = metrics.precision_score(y_test, y_pred)
    models_svm[goterm]=svm_model

len(models_svm)

939

Final model AUC

GO_terms_auc_svm_df_final = pd.DataFrame(list(GO_terms_auc_svm_final.items()),columns = ['goterm','auc']).set_index("goterm")
GO_terms_auc_svm_df_final = GO_terms_auc_svm_df_final.dropna()
GO_terms_auc_svm_df_final.sort_values(by=["auc"], ascending=False)

	auc
goterm
GO:0036289	1.000000
GO:0060440	0.998540
GO:0043162	0.995455
GO:0070059	0.994760
GO:0071364	0.994109
GO:1901029	0.994048
GO:0072384	0.993636
GO:0051453	0.993393
GO:0001556	0.991972
GO:0090201	0.991808
GO:0010750	0.990909
GO:0016573	0.990783
GO:1903800	0.990573
GO:1904950	0.989945
GO:1902455	0.989091
GO:0042149	0.987697
GO:0034983	0.987273
GO:1990403	0.985909
GO:0071353	0.985587
GO:0006275	0.984226
GO:0010971	0.984091
GO:0006869	0.983409
GO:0001779	0.983182
GO:0051973	0.981651
GO:0060749	0.980895
GO:0042771	0.980633
GO:0072655	0.980455
GO:0061734	0.980455
GO:0045636	0.980178
GO:0045737	0.980084
GO:1902236	0.979762
GO:0060632	0.979545
GO:0016575	0.978731
GO:0042659	0.977727
GO:0046628	0.977376
GO:1902042	0.977273
GO:0098780	0.975909
GO:0046902	0.975849
GO:0051607	0.975552
GO:0006401	0.974678
GO:0017157	0.974040
GO:0032740	0.973856
GO:0006270	0.973848
GO:0046666	0.973570
GO:0008045	0.972603
GO:0006303	0.972553
GO:0042177	0.972431
GO:0060020	0.972290
GO:0006360	0.972095
GO:2001021	0.971520
GO:0042733	0.971364
GO:0016572	0.971342
GO:0070932	0.970909
GO:2001257	0.970909
GO:0001782	0.970384
GO:0006261	0.970112
GO:1905564	0.969834
GO:2000757	0.969545
GO:0051354	0.969091
GO:0072284	0.969069
GO:0051926	0.968891
GO:0043407	0.968585
GO:0034394	0.968096
GO:0050870	0.967621
GO:0046898	0.967143
GO:0031047	0.967115
GO:0016925	0.966364
GO:0035790	0.966361
GO:0006417	0.965261
GO:0032469	0.965008
GO:0035195	0.964816
GO:0021782	0.964091
GO:0070584	0.963810
GO:0051384	0.961083
GO:0002326	0.960811
GO:2000773	0.960310
GO:0050729	0.959779
GO:0046942	0.959480
GO:0035249	0.959091
GO:0045821	0.958904
GO:0099111	0.958880
GO:0071670	0.958851
GO:0006367	0.958333
GO:1905278	0.958270
GO:0010559	0.957929
GO:0006959	0.957854
GO:0018205	0.957782
GO:0035860	0.957768
GO:0031640	0.957381
GO:0007059	0.957268
GO:0070373	0.956762
GO:0030282	0.956762
GO:0001658	0.956522
GO:0030890	0.956075
GO:0035754	0.955757
GO:0010832	0.955455
GO:0099173	0.955238
GO:0021695	0.955238
GO:0045727	0.955026
GO:0002862	0.954696
GO:0014827	0.954432
GO:0016579	0.953923
GO:0002718	0.953854
GO:0071320	0.953746
GO:0051281	0.953182
GO:0042552	0.953182
GO:0000086	0.953095
GO:0032147	0.952991
GO:0032436	0.952499
GO:0010592	0.952273
GO:0006694	0.951735
GO:0033141	0.951735
GO:0071480	0.951429
GO:0006612	0.951118
GO:0048011	0.950729
GO:1903077	0.950714
GO:0033619	0.950455
GO:0006352	0.950306
GO:0001662	0.950221
GO:0010039	0.950040
GO:0090314	0.949147
GO:0034502	0.949074
GO:0014823	0.948954
GO:2001240	0.948220
GO:0007617	0.948182
GO:0032743	0.947281
GO:0006310	0.947141
GO:0006605	0.946678
GO:0006975	0.946204
GO:2000739	0.946101
GO:1902459	0.945909
GO:0007626	0.945701
GO:0023019	0.945116
GO:0003376	0.944700
GO:0006576	0.944346
GO:0038007	0.943690
GO:0050728	0.943637
GO:0032922	0.942661
GO:0045740	0.942465
GO:1900118	0.942381
GO:0010952	0.942143
GO:1905710	0.942143
GO:1902166	0.942128
GO:0008637	0.941950
GO:2000010	0.941865
GO:0055118	0.941679
GO:0000423	0.941364
GO:0043154	0.941156
GO:0048701	0.940775
GO:0008210	0.940749
GO:1900272	0.940171
GO:0060997	0.939809
GO:0007263	0.939545
GO:2000379	0.939167
GO:1900020	0.939091
GO:0050896	0.938915
GO:0016485	0.938636
GO:0043966	0.938376
GO:0002437	0.938295
GO:2000300	0.937318
GO:0140013	0.937095
GO:0034767	0.936758
GO:0031648	0.936624
GO:0007026	0.936364
GO:0032024	0.936149
GO:0030193	0.936040
GO:0010212	0.935098
GO:0006457	0.934641
GO:0032729	0.934420
GO:0030593	0.934413
GO:0010575	0.934272
GO:0008064	0.933643
GO:0008286	0.932331
GO:0001818	0.932128
GO:0030513	0.931404
GO:0060766	0.931364
GO:0006396	0.931346
GO:0006919	0.931342
GO:0038096	0.930886
GO:0001553	0.930810
GO:0045580	0.930407
GO:0046326	0.930406
GO:0035025	0.930294
GO:1903146	0.929091
GO:0060444	0.929091
GO:0006412	0.928571
GO:0048536	0.928290
GO:0002819	0.927685
GO:0048704	0.927370
GO:0051054	0.927333
GO:0090184	0.927099
GO:1900006	0.926941
GO:2000134	0.926917
GO:0046889	0.926822
GO:0043123	0.926512
GO:0070842	0.926364
GO:0046329	0.926364
GO:0006898	0.925891
GO:0006368	0.925841
GO:1905897	0.925743
GO:0030048	0.925591
GO:0042180	0.925076
GO:0035909	0.924883
GO:0051209	0.924065
GO:0030308	0.923951
GO:0043170	0.923707
GO:0035726	0.922783
GO:0031663	0.922727
GO:0000209	0.922119
GO:0009165	0.921544
GO:0002720	0.921427
GO:0006096	0.921292
GO:1902036	0.921254
GO:0071549	0.921066
GO:0007528	0.920950
GO:0090090	0.920930
GO:0042472	0.920455
GO:0031056	0.920429
GO:0050864	0.920262
GO:0060789	0.920000
GO:0007389	0.919762
GO:0048743	0.919572
GO:0030705	0.919116
GO:0060179	0.919091
GO:0045739	0.918823
GO:0043627	0.917977
GO:0040018	0.917659
GO:2001243	0.917078
GO:0090037	0.917056
GO:0040016	0.915987
GO:0043552	0.915951
GO:0001666	0.915013
GO:0010508	0.914755
GO:0033690	0.914545
GO:0098586	0.914419
GO:0043922	0.914091
GO:0035994	0.914021
GO:0031398	0.913694
GO:0042093	0.913524
GO:0032410	0.913182
GO:1901224	0.913182
GO:0006839	0.913167
GO:0045907	0.912844
GO:2000278	0.912619
GO:2001236	0.912563
GO:0048170	0.912474
GO:0071839	0.912217
GO:0031507	0.911552
GO:0060391	0.911011
GO:0032148	0.910451
GO:0070102	0.910000
GO:0030878	0.909762
GO:0035162	0.909463
GO:0051225	0.909314
GO:0002931	0.909064
GO:0007411	0.908683
GO:0008625	0.908500
GO:0035788	0.908313
GO:0010921	0.907360
GO:0048266	0.906977
GO:0010977	0.906667
GO:0050910	0.906656
GO:0045732	0.906062
GO:0046620	0.905714
GO:0035855	0.905551
GO:0030316	0.905551
GO:0006469	0.905340
GO:0090263	0.905136
GO:0021953	0.904874
GO:0060312	0.904790
GO:0006260	0.904703
GO:0030521	0.904434
GO:0008016	0.904091
GO:0010727	0.904091
GO:0030509	0.904035
GO:0007498	0.903914
GO:0050769	0.903592
GO:0050792	0.903414
GO:0009582	0.903167
GO:0007098	0.902745
GO:0002821	0.902464
GO:0071276	0.902162
GO:0007286	0.901132
GO:0045088	0.900952
GO:0055003	0.900943
GO:0035767	0.900748
GO:0045987	0.900474
GO:0061029	0.900474
GO:0033327	0.900465
GO:0000422	0.900374
GO:0010976	0.900117
GO:0008354	0.899895
GO:0070528	0.899726
GO:0006807	0.899601
GO:0045833	0.899128
GO:1905065	0.898923
GO:0007018	0.898915
GO:0007422	0.898647
GO:0048484	0.898636
GO:0032467	0.898182
GO:0050795	0.897909
GO:0030539	0.897909
GO:0048538	0.897833
GO:0032355	0.897646
GO:0007416	0.897554
GO:0021575	0.897509
GO:0060348	0.897410
GO:0001569	0.897282
GO:0060384	0.897171
GO:0031069	0.897099
GO:0050918	0.897059
GO:0035584	0.896905
GO:0051046	0.896369
GO:0043129	0.896233
GO:0001843	0.896024
GO:0046330	0.895444
GO:0007030	0.895429
GO:0048873	0.895092
GO:0000724	0.894922
GO:0007202	0.894511
GO:1903053	0.894419
GO:0003338	0.894238
GO:1901990	0.894150
GO:0060644	0.893917
GO:0043161	0.893782
GO:0030838	0.892727
GO:0001946	0.892571
GO:0072210	0.892039
GO:0030101	0.892003
GO:0050731	0.892003
GO:0010613	0.891865
GO:0030325	0.891865
GO:0048714	0.891783
GO:0048008	0.891667
GO:0001823	0.890989
GO:0016239	0.890496
GO:0030216	0.890460
GO:0071300	0.890341
GO:0032008	0.889952
GO:0061045	0.889881
GO:0051894	0.889619
GO:0030010	0.889612
GO:0031016	0.889533
GO:0001942	0.889526
GO:1902533	0.889155
GO:0016358	0.888660
GO:0001501	0.888280
GO:0051092	0.888251
GO:0016601	0.887883
GO:0097067	0.887324
GO:0009306	0.887019
GO:0048167	0.886555
GO:0050921	0.886315
GO:1990384	0.886268
GO:0046883	0.886202
GO:0007519	0.886154
GO:0043270	0.885881
GO:0003007	0.885720
GO:0071900	0.885420
GO:0007585	0.885391
GO:2001214	0.885258
GO:0071456	0.884685
GO:0016567	0.884594
GO:0060740	0.882856
GO:0035094	0.882732
GO:0072073	0.882732
GO:0060612	0.881602
GO:0060325	0.881498
GO:0045668	0.881347
GO:0042531	0.881332
GO:0010038	0.881167
GO:0071333	0.880972
GO:0006939	0.880907
GO:0090141	0.880907
GO:0046718	0.880697
GO:0051770	0.880461
GO:0033627	0.880455
GO:0048149	0.880352
GO:0002685	0.880291
GO:0043029	0.880195
GO:0038033	0.879699
GO:0055119	0.879336
GO:0003300	0.878843
GO:0005984	0.878788
GO:0002218	0.878773
GO:0072239	0.878669
GO:0031103	0.878667
GO:0048557	0.878638
GO:1901987	0.878627
GO:0060048	0.877703
GO:0045637	0.877659
GO:2001234	0.877406
GO:0038083	0.876762
GO:0071277	0.876323
GO:0048839	0.876278
GO:0000723	0.875714
GO:0060627	0.875648
GO:0035022	0.874811
GO:0007435	0.874669
GO:2001241	0.874309
GO:0002062	0.874091
GO:0035234	0.873792
GO:0034976	0.873754
GO:0007584	0.872411
GO:0002318	0.872408
GO:0001975	0.872354
GO:0071230	0.871837
GO:0034446	0.871788
GO:0070933	0.871364
GO:0030072	0.871331
GO:0071897	0.871171
GO:0035733	0.870478
GO:0032967	0.870403
GO:0048675	0.870071
GO:0060571	0.870035
GO:0050920	0.869917
GO:0050678	0.869106
GO:0034405	0.869048
GO:0051150	0.868932
GO:0001934	0.868720
GO:0010507	0.868700
GO:1904707	0.868636
GO:0050821	0.868325
GO:0006811	0.868262
GO:0070588	0.868155
GO:0014911	0.867596
GO:0090280	0.867440
GO:0008630	0.867386
GO:1901796	0.867386
GO:0051056	0.867368
GO:0051321	0.865996
GO:0051051	0.865833
GO:0051902	0.865573
GO:0097009	0.865089
GO:0060271	0.865061
GO:0045930	0.864995
GO:0035304	0.864977
GO:0051899	0.864866
GO:0033028	0.864808
GO:0018108	0.864767
GO:1900087	0.864434
GO:0010467	0.863952
GO:0035019	0.863557
GO:0006687	0.863557
GO:0001824	0.863532
GO:0033689	0.863522
GO:0071392	0.863443
GO:0035264	0.863252
GO:0046632	0.862800
GO:0034605	0.862619
GO:0032091	0.862599
GO:0072659	0.862358
GO:0051901	0.861670
GO:0006357	0.861504
GO:0042475	0.861448
GO:0045747	0.861374
GO:0072006	0.860598
GO:0042220	0.860483
GO:0006937	0.860353
GO:0006511	0.860111
GO:0010718	0.859229
GO:0035924	0.859169
GO:0090398	0.859050
GO:0031532	0.858981
GO:1904062	0.858745
GO:2000251	0.858605
GO:0014068	0.858156
GO:0048146	0.858102
GO:0051090	0.857756
GO:0034765	0.857317
GO:0007229	0.856812
GO:0007158	0.856712
GO:1901031	0.856712
GO:0061351	0.856372
GO:1904019	0.856183
GO:0048812	0.856107
GO:0060437	0.855565
GO:0034766	0.854758
GO:0033143	0.854574
GO:0007269	0.854497
GO:0032516	0.854484
GO:0036120	0.854433
GO:0090068	0.853947
GO:0046854	0.853881
GO:0010811	0.853842
GO:0060976	0.853774
GO:0060045	0.853680
GO:0021549	0.853311
GO:0043534	0.853142
GO:0038084	0.853135
GO:0046427	0.852947
GO:0030324	0.852866
GO:0048010	0.852488
GO:0097193	0.852297
GO:0048286	0.852143
GO:0006468	0.851852
GO:0060326	0.851772
GO:0034097	0.851678
GO:0016071	0.851667
GO:0036324	0.851085
GO:1903010	0.851085
GO:0002327	0.850962
GO:0001570	0.850955
GO:0043536	0.850601
GO:0043406	0.850494
GO:0045347	0.850455
GO:0001701	0.850196
GO:0019222	0.849913
GO:0051403	0.849741
GO:0097021	0.849170
GO:0043467	0.848706
GO:0045766	0.848621
GO:0060562	0.848060
GO:0030001	0.847486
GO:0006810	0.847446
GO:0031667	0.847070
GO:0048565	0.846000
GO:0019827	0.845649
GO:0007565	0.845356
GO:0009966	0.844893
GO:0055085	0.844768
GO:0043114	0.844749
GO:0002548	0.844626
GO:2000377	0.844341
GO:0030198	0.844187
GO:0032386	0.844167
GO:0031929	0.844150
GO:0035306	0.843956
GO:0006897	0.843955
GO:0051301	0.843815
GO:0001656	0.843809
GO:0042060	0.843773
GO:0031109	0.843563
GO:0000122	0.843521
GO:0043124	0.843017
GO:0001837	0.842638
GO:1902275	0.841719
GO:0051261	0.841719
GO:0051924	0.841520
GO:0002250	0.841465
GO:0030336	0.841059
GO:0046631	0.840909
GO:0016055	0.840841
GO:0033077	0.840735
GO:0048741	0.840370
GO:0007266	0.839667
GO:0001938	0.838948
GO:0043586	0.838898
GO:0008277	0.837920
GO:0043303	0.837858
GO:0070662	0.837526
GO:0060374	0.836916
GO:0045087	0.836889
GO:0034220	0.836107
GO:0032388	0.835532
GO:0048568	0.835305
GO:0050866	0.835227
GO:0009058	0.834946
GO:1902074	0.834912
GO:0043244	0.834906
GO:0008542	0.834749
GO:0045055	0.834433
GO:0045444	0.834286
GO:0046578	0.834019
GO:0046777	0.833773
GO:0001889	0.833595
GO:0008584	0.833556
GO:0045840	0.833536
GO:0002366	0.833530
GO:0007049	0.833424
GO:0046474	0.833392
GO:0019233	0.833182
GO:0000165	0.832917
GO:0051258	0.832656
GO:0032956	0.832450
GO:0022612	0.832326
GO:0051050	0.832281
GO:0043392	0.831905
GO:0031274	0.831814
GO:0051702	0.831506
GO:0010564	0.831039
GO:0031099	0.830615
GO:1905563	0.830607
GO:0030318	0.830136
GO:0048598	0.829861
GO:0007165	0.829719
GO:1901988	0.829474
GO:0007186	0.829429
GO:0033157	0.829023
GO:0019221	0.829000
GO:0000278	0.828800
GO:0042310	0.828784
GO:1901300	0.828616
GO:0006909	0.828497
GO:0030154	0.828332
GO:0002573	0.827001
GO:0045429	0.826889
GO:0051223	0.826823
GO:0016570	0.826822
GO:0030163	0.826442
GO:0009791	0.826355
GO:0090630	0.826069
GO:0032409	0.825426
GO:0048477	0.824868
GO:0034644	0.824849
GO:0007346	0.824841
GO:0046651	0.824539
GO:0051171	0.823977
GO:0000302	0.823816
GO:0048608	0.823637
GO:0032940	0.823481
GO:0008610	0.823469
GO:0010628	0.823151
GO:1903078	0.822244
GO:0016032	0.821730
GO:0009888	0.821458
GO:0016042	0.821320
GO:0007259	0.820971
GO:0008544	0.820813
GO:0000077	0.820719
GO:0021766	0.820586
GO:0001817	0.819733
GO:0001932	0.819683
GO:0002053	0.819493
GO:0072593	0.819390
GO:0009887	0.819242
GO:0006753	0.818971
GO:0071383	0.818684
GO:0007015	0.818627
GO:0001819	0.818452
GO:0007275	0.818394
GO:1903829	0.818083
GO:0002244	0.818060
GO:0051898	0.817795
GO:0009410	0.817265
GO:0030335	0.817025
GO:0061024	0.816492
GO:0007173	0.816349
GO:0050900	0.816242
GO:0060395	0.815909
GO:0009755	0.815667
GO:0045860	0.815613
GO:0050872	0.815367
GO:0007612	0.814548
GO:0000082	0.814519
GO:0050852	0.814267
GO:0043408	0.813977
GO:0002009	0.813874
GO:0019752	0.813530
GO:0001822	0.813506
GO:0007179	0.813500
GO:0051049	0.813439
GO:0010033	0.813421
GO:1901135	0.813379
GO:1900180	0.813213
GO:0033554	0.813172
GO:0007204	0.813136
GO:0044770	0.812960
GO:0001755	0.812831
GO:0001541	0.812614
GO:0006470	0.811795
GO:0009743	0.811594
GO:0033993	0.811585
GO:0035265	0.811041
GO:0051496	0.811040
GO:0007162	0.810927
GO:0030218	0.809955
GO:0006139	0.809816
GO:0070374	0.808642
GO:0006298	0.808612
GO:0009056	0.808581
GO:0070507	0.808431
GO:0071363	0.808295
GO:0050680	0.808234
GO:0007169	0.807939
GO:0001894	0.807870
GO:0000902	0.806862
GO:0009617	0.806711
GO:1902904	0.806512
GO:0030097	0.806125
GO:0007399	0.805949
GO:0050853	0.805230
GO:0051726	0.804914
GO:0008360	0.804780
GO:0050863	0.804772
GO:0010629	0.804702
GO:0032880	0.804305
GO:0021795	0.804198
GO:0046488	0.804184
GO:0031032	0.804004
GO:0045595	0.803077
GO:0006936	0.802344
GO:0045793	0.802149
GO:0071222	0.801980
GO:0051897	0.801416
GO:0006606	0.800953
GO:0006886	0.800872
GO:0030307	0.800490
GO:0048738	0.800331
GO:0010821	0.800220
GO:0051247	0.800154
GO:0042752	0.800120
GO:0032835	0.800025
GO:0033138	0.799982
GO:1903578	0.799701
GO:0050673	0.798946
GO:0006997	0.798672
GO:0060341	0.798662
GO:0006281	0.798556
GO:0042391	0.798475
GO:0050808	0.797394
GO:0007267	0.797360
GO:0050865	0.797107
GO:0018105	0.797070
GO:0060560	0.796569
GO:0071478	0.796131
GO:0018107	0.796045
GO:0019216	0.795977
GO:0023061	0.795969
GO:0036473	0.795897
GO:0051147	0.795455
GO:0006996	0.794900
GO:0030217	0.794761
GO:0070527	0.794579
GO:0050804	0.793936
GO:0060021	0.793808
GO:0045321	0.793792
GO:0046034	0.792891
GO:1904646	0.792812
GO:0030182	0.792624
GO:0002764	0.790893
GO:0007596	0.790844
GO:0043542	0.790474
GO:0006355	0.790400
GO:0010638	0.790227
GO:0042110	0.789916
GO:2000811	0.789519
GO:0045785	0.789271
GO:0001952	0.789204
GO:0048709	0.787833
GO:0016192	0.787802
GO:0002320	0.787705
GO:0045944	0.787650
GO:0035051	0.787216
GO:0070663	0.786907
GO:0046486	0.786765
GO:0006914	0.786701
GO:0071407	0.786480
GO:0048468	0.786471
GO:0043065	0.786229
GO:1902532	0.786009
GO:0033044	0.785934
GO:0031333	0.785379
GO:0071417	0.785307
GO:0016241	0.785238
GO:0007268	0.785105
GO:0007010	0.785047
GO:0002443	0.783904
GO:2000270	0.783308
GO:0001764	0.782709
GO:0051174	0.781935
GO:0034329	0.781439
GO:0043549	0.781269
GO:0010595	0.781136
GO:2001020	0.780899
GO:0050776	0.780250
GO:0007159	0.780220
GO:0048041	0.780105
GO:0016236	0.779569
GO:0048638	0.778556
GO:0042551	0.778521
GO:0007517	0.778474
GO:0032869	0.777921
GO:0051649	0.777222
GO:0009725	0.777056
GO:0030855	0.776398
GO:0002040	0.776347
GO:0071310	0.775759
GO:0042063	0.775499
GO:0009266	0.775262
GO:0048469	0.774721
GO:0042307	0.774054
GO:0032879	0.772742
GO:0002376	0.772696
GO:0055082	0.772549
GO:0016070	0.772150
GO:0060840	0.771853
GO:0010632	0.771656
GO:0007219	0.771429
GO:0051341	0.770833
GO:0060416	0.770267
GO:0090050	0.770256
GO:0002274	0.770035
GO:0009968	0.768538
GO:0009416	0.768293
GO:0009653	0.767978
GO:0030183	0.767941
GO:0007507	0.766819
GO:0007283	0.766625
GO:0048589	0.766590
GO:0050790	0.766284
GO:0065003	0.765562
GO:0030032	0.765559
GO:0048103	0.765258
GO:0006954	0.764565
GO:0048878	0.764329
GO:0007420	0.764092
GO:0030168	0.762921
GO:0006629	0.761422
GO:0006644	0.760398
GO:0001525	0.760172
GO:0120035	0.759979
GO:0034103	0.759958
GO:0014070	0.759563
GO:0044255	0.758471
GO:0051098	0.758377
GO:0051641	0.757853
GO:0034599	0.756607
GO:0043473	0.756079
GO:0036092	0.755500
GO:0048863	0.755435
GO:2000352	0.754950
GO:0030162	0.754327
GO:0042325	0.754119
GO:0008202	0.754059
GO:0033628	0.753988
GO:0051146	0.753713
GO:0010243	0.753077
GO:0043524	0.752485
GO:0003014	0.752381
GO:0002684	0.752271
GO:0001763	0.751863
GO:0051145	0.751530
GO:0045596	0.750733
GO:0000226	0.750411
GO:0031175	0.749603
GO:0007155	0.749178
GO:0002064	0.748667
GO:0045597	0.748593
GO:0040008	0.748313
GO:0060485	0.746706
GO:0006508	0.746456
GO:0097191	0.746084
GO:0016477	0.745481
GO:0005975	0.745307
GO:0043066	0.745136
GO:0050890	0.744664
GO:0007265	0.744598
GO:0032092	0.743751
GO:0051017	0.743352
GO:0007005	0.742652
GO:0043434	0.742583
GO:0003158	0.742221
GO:0042113	0.742005
GO:0120162	0.741508
GO:0051881	0.740169
GO:0030522	0.740000
GO:0007160	0.739980
GO:0048511	0.737766
GO:0044281	0.736585
GO:0007568	0.736500
GO:0007610	0.735604
GO:0035556	0.734890
GO:0048017	0.734281
GO:0006325	0.734050
GO:0006915	0.733434
GO:0008284	0.731624
GO:0045165	0.731183
GO:0002682	0.730932
GO:0022414	0.730731
GO:0097190	0.730349
GO:0051494	0.729426
GO:0051128	0.728822
GO:0043254	0.728497
GO:0098609	0.727096
GO:0006338	0.726229
GO:0007423	0.725167
GO:0001649	0.721908
GO:0048661	0.721041
GO:0010941	0.719507
GO:1900407	0.716777
GO:0007166	0.714859
GO:0002683	0.708778
GO:1902903	0.708773
GO:0008285	0.705969
GO:0030900	0.704312
GO:0034504	0.704188
GO:0033365	0.703782
GO:0070997	0.703482
GO:0033043	0.697664
GO:0051249	0.687925
GO:0008104	0.675076
GO:0033002	0.627125
GO:0042593	0.364293
GO:0071887	0.359703
GO:0044262	0.349744
GO:0051640	0.348052
GO:0051000	0.299934
GO:0050778	0.290903
GO:0007156	0.278928
GO:0008361	0.265902
GO:0070301	0.262988
GO:0022407	0.258553
GO:0015031	0.257560
GO:0043525	0.248848
GO:0051353	0.242570
GO:0043086	0.239824
GO:0045471	0.229314
GO:0051497	0.208992
GO:0031529	0.208648
GO:0099504	0.206822
GO:0043547	0.194217
GO:1904659	0.191457
GO:0031334	0.184335
GO:0046677	0.183479
GO:0015980	0.180476
GO:0060291	0.175234
GO:0009259	0.166290
GO:0060173	0.162212
GO:0042632	0.145299
GO:0046890	0.144186
GO:0032760	0.142722
GO:0051302	0.135000
GO:0031295	0.134696
GO:0019318	0.123006
GO:0010951	0.120040
GO:0021987	0.119137
GO:0006163	0.118024
GO:0030041	0.107955
GO:0001892	0.106324
GO:0030512	0.105991
GO:0060079	0.105991
GO:0050770	0.098547
GO:0051928	0.097553
GO:0031397	0.094042
GO:0060041	0.082956
GO:0051047	0.076258
GO:0019722	0.041730
GO:0090042	0.035699

sns.set(rc={'figure.figsize':(6,4)})
perc = str(round((100*len(GO_terms_auc_svm_df_final[GO_terms_auc_svm_df_final["auc"]>0.7])/len(GO_terms_auc_svm_df_final)),2))+"%"
N, bins, patches = plt.hist(GO_terms_auc_svm_df_final, color=CB_color_cycle[6],bins=50, linewidth=0.1)

for i in range(0,len(bins)-1):
    if bins[i]>0.7:
        patches[i].set_facecolor(CB_color_cycle[2])

plt.xlabel("AUC (logistic 1)", fontsize=16)  
plt.title(perc, fontsize=16)
# con el que mejor funciona es con la suma normal del attribution 

Text(0.5, 1.0, '94.68%')

Final model AUPR

GO_terms_aupr_svm_df_final = pd.DataFrame(list(GO_terms_aupr_svm_final.items()),columns = ['goterm','aupr']).set_index("goterm")
GO_terms_aupr_svm_df_final = GO_terms_aupr_svm_df_final.dropna()
GO_terms_aupr_svm_df_final.sort_values(by=["aupr"], ascending=False).head()

	aupr
goterm
GO:0036289	1.000000
GO:0050896	0.995438
GO:0043170	0.989680
GO:0006807	0.987396
GO:0060440	0.978213

# TENGO PROBLEMA CON EL RECALL 
sns.set(rc={'figure.figsize':(5,3)})
perc = str(round((100*len(GO_terms_aupr_svm_df_final[GO_terms_aupr_svm_df_final["aupr"]>0.7])/len(GO_terms_aupr_svm_df_final)),2))+"%"
N, bins, patches = plt.hist(GO_terms_aupr_svm_df_final, color=CB_color_cycle[6],bins=50, linewidth=0.1)
for i in range(0,len(bins)-1):
    if bins[i]>0.7:
        patches[i].set_facecolor(CB_color_cycle[3])

plt.xlabel("AUPR", fontsize=16)  
plt.title(perc, fontsize=16)

Text(0.5, 1.0, '20.02%')

Predict for a new drug

Make predictions

unknown = list(set(attribution_data_all.columns)-set(attribution_data_annotated.columns))

Get the probabilities for all unknown drugs

predictions = {}
distances = {}
probabilities_unknown = pd.DataFrame()
preds_unknown = pd.DataFrame()

for drug in unknown:
    probabilities = {}
    for goterm in models_svm.keys():

        list_nodes = list(models_svm[goterm].feature_names_in_) # Extract the feature names from the model (those are the attributions we need)

        score = attribution_data_all.loc[list_nodes][drug].to_frame().T 
        score_mod = score.divide(attribution_data_annotated.loc[list_nodes].T.std()).fillna(0) #divide by std of each neuron, only use drugs that trained the models

        predictions[goterm]=models_svm[goterm].predict(score_mod)
        probabilities[goterm] = models_svm[goterm].predict_proba(score_mod)[::,1]  # platt values
        # distances[goterm] = models_svm[goterm].decision_function(score_mod)
        
    drug_probs = pd.DataFrame.from_dict(probabilities).T
    drug_probs.columns = [drug]
    drug_preds = pd.DataFrame.from_dict(predictions).T
    drug_preds.columns = [drug]    
    probabilities_unknown = pd.concat([probabilities_unknown,drug_probs], axis=1)
    preds_unknown = pd.concat([preds_unknown,drug_preds], axis=1)
    print(drug)

brd-k19103580-001-01-2
nvp-bhg712
wh-4-023
pd173074
cbpnzqvsjqdfbe-rerlvdevsa-n
n-(2,5-dimethoxyphenyl)sulfonyl-n-(4-methoxyphenyl)benzamide
brd-k33514849-001-01-9
chembl3182697
dfsdbfjuwanyes-ubwkhrtasa-n
nvp-adw742
sb 225002
schembl10436373
stf-62247
zm-447439
gsk269962a
schembl12469828
schembl2139153
azd7545
mira-1
wee1 inhibitor
achp
chembl2203525
brd-k49290616-001-01-9
nvp-231
pha-665752
jq1
n-[(2r,3s)-2-[[cyclopropylmethyl(methyl)amino]methyl]-5-[(2r)-1-hydroxypropan-2-yl]-3-methyl-6-oxo-3,4-dihydro-2h-1,5-benzoxazocin-8-yl]-1-methyl-4-imidazolesulfonamide
otkwubxkthwzke-fuopvmcbsa-n
bms-345541;cc1=cc2=c(c=c1)n=c(c3=nc=c(n23)c)nccn.cl
cid5951923
ml-030
cct036477
pluripotin
nutlin-3a
skepinone-l
gsk-j4
(-)-rapamycin
hhdwuyjenprcsp-uttpphfysa-n
r406 (free base)
n-[[(4r,5r)-2-[(2r)-1-hydroxypropan-2-yl]-4-methyl-8-(4-methylpent-1-ynyl)-1,1-dioxo-4,5-dihydro-3h-6,1$l^{6},2-benzoxathiazocin-5-yl]methyl]-n-methyl-2-pyrazinecarboxamide
plx-4720
chebi:119735
pdk1 inhibitor
pf-573228
jq1 + mk-0752
cay10594
fti-277
gw843682x
sz4ta2
bix 02189
chembl2180739
chm-1
s-trityl-l-cysteine
qs11
hg6-64-1
lomeguatrib
rad51 inhibitor b02
bms-509744
bms614
brd-k09587429-001-01-3
gsk429286a
bx-912
fawugygebhaqbu-ppexnqrjsa-n
schembl2066172
schembl618594
ethyl 5,5,7,7-tetramethyl-2-(5-nitrothiophene-2-carboxamido)-4,5,6,7-tetrahydrothieno[2,3-c]pyridine-3-carboxylate
ar-42
fttyfnwrwdlflp-uhfffaoysa-n
n'-(2-pyrrolylidenemethyl)-2-(2,4,6-trichlorophenoxy)acetohydrazide
methylstat
nsc87877
opahmanwvumwaw-ghfzsmqjsa-n
wp-1130
dacarbazine
schembl6874948
mk-0752
brd-k35716340-001-01-2
brd-a63646118-001-02-6
brd-k62801835-001-01-0
shikonin
nsc 23766
selisistat
brd-k50799972-001-01-3
homoharringtonine
unc0321
sr8278
erastin
schembl12180851
schembl1710881
brd-k17060750-001-01-0
dbeq
jq1 + schembl2671349
mnulegdcpyonbu-pamdcedjsa-n
schembl13833463
gdc-0879
mdivi-1
chembl515416
brd-k53792571-003-01-6
n-[(2r,3r)-5-[(2s)-1-hydroxypropan-2-yl]-3-methyl-2-[[methyl-[(1-naphthalenylamino)-oxomethyl]amino]methyl]-6-oxo-3,4-dihydro-2h-1,5-benzoxazocin-10-yl]-4-pyridinecarboxamide
n-[[(2s,3s)-8-[2-(1-hydroxycyclopentyl)ethynyl]-5-[(2s)-1-hydroxypropan-2-yl]-3-methyl-6-oxo-3,4-dihydro-2h-pyrido[2,3-b][1,5]oxazocin-2-yl]methyl]-n-methyl-4-oxanecarboxamide
gsk4112
mkwlqyduwjbeku-lwsjdiafsa-n
chembl3183639
khs101
ch 55
narciclasine
betulinic acid
sb-590885
brd-k20514654-001-01-8
dacinostat
unc0638
nsc207895
tw-37
11-cis retinoic acid
bibr 1532
dichloroplatinum diammoniate
5-azacytidine
gqrreykspjmlaw-ygnumjmvsa-n
chembl2058177
c6 ceramide
camptothecin
schembl12474870
agk2
ski ii
chembl24850
icg-001
n-[(2s,3s)-2-[(dimethylamino)methyl]-5-[(2r)-1-hydroxypropan-2-yl]-3-methyl-6-oxo-3,4-dihydro-2h-1,5-benzoxazocin-10-yl]-2,5-dimethyl-3-pyrazolecarboxamide
vx-11e
cct 018159
wfygwjxipugujf-uhfffaoysa-n
mls000571394
aacocf3
naphtho(2,1-b)furan, 1-methyl-2-nitro-
n-[(2s,3s)-5-[(2r)-1-hydroxypropan-2-yl]-3-methyl-2-[[methyl-[(1-naphthalenylamino)-oxomethyl]amino]methyl]-6-oxo-2,3,4,7-tetrahydro-1,5-benzoxazonin-9-yl]-4-pyridinecarboxamide
brd-k25737009-001-01-2
jnk inhibitor viii
spautin-1
ic-87114
sr1001
16beta-bromoandrosterone
schembl2586580
nvp-tae684
cgp-60474
jw 480
fhtvasvneuemiv-lwsjdiafsa-n
ethyl 4-[4-[(5-nitrofuran-2-yl)methylidene]-3,5-dioxopyrazolidin-1-yl]benzoate
dmog
schembl15422095
chembl2132053
brd-k02251932-001-01-3
bms-536924;cc1=cc(=cc2=c1n/c(=c\3/c(=cc=nc3=o)nc[c@h](c4=cc(=cc=c4)cl)o)/n2)n5ccocc5
nsc60043
ng25
cid-2858522
schembl13737661
ikk-3 inhibitor
brd7880
smer-3
cx-5461
am580
elesclomol
chembl2381520
hc-067047
schembl17821363
niclosamide
n-[(2r,3s)-5-[(2r)-1-hydroxypropan-2-yl]-3-methyl-2-(methylaminomethyl)-6-oxo-2,3,4,7-tetrahydro-1,5-benzoxazonin-9-yl]methanesulfonamide
thapsigargin
brd1172
schembl1914213
i-bet-762
brd-k58306044-001-01-3
a-770041
chembl585951
glutaminase c-in-1
ql47
chembl2143553
cytochalasin b
n1-[2-(1h-indol-3-yl)ethyl]-n3-pyridin-4-ylbenzene-1,3-diamine
curcumin, curcuma longa l.
pifithrin
schembl16479156
chlorambucil
schembl15444220
zinc113660258
yk-4-279
pci-34051
fh535
schembl916391
n-(2-(4-(2-oxo-2,3-dihydro-1h-benzo[d]imidazol-1-yl)piperidin-1-yl)ethyl)-2-naphthamide
brd-k30019337-001-01-1
nvp-bsk805
chembl2356172
unc-0638 + schembl2671349
ki8751
az3146
isx-9
schembl13741284
ku-0063794
sb-431542
tpca-1
pdipalloxofubu-uhfffaoysa-n
(-)-epigallocatechin gallate
bleomycin
rsk inhibitor fmk
n9-isopropyl-olomoucine
mgcd-265
ml031
mg-132
n-[3-(1h-benzimidazol-2-yl)-5-(1-piperazinylmethyl)phenyl]-2-quinoxalinecarboxamide
le 135
phloretin
schembl2085358
abt-737
jw74
pf 750
chembl436817
cp-466722
myricetin
kcbbhekxehmwfw-yqzfvpmhsa-n
gw-405833
brd-6929
brd-k52037352-001-01-6
stemregenin 1
iu-1
apicidin
spox1_002925
brd6708
darinaparsin
wpttvjltnawyao-cdypjpissa-n
mi-2
ak174031
chebi:94975
nsc373989
snx-2112
ac-55649
gsk-650394
cyclopamine
o6-benzylguanine
pd153035
ipa-3
chir-99021
n-[[(4s,5r)-8-[2-(2-fluorophenyl)ethynyl]-2-[(2s)-1-hydroxypropan-2-yl]-4-methyl-1,1-dioxo-4,5-dihydro-3h-6,1$l^{6},2-benzoxathiazocin-5-yl]methyl]-n-methyl-2-pyridin-4-ylacetamide
su11274
chebi:94110
brd-k49456190-001-01-0
cct007093
schembl18216694
n-[(2r,3s)-5-[(2s)-1-hydroxypropan-2-yl]-3-methyl-2-(methylaminomethyl)-6-oxo-3,4-dihydro-2h-1,5-benzoxazocin-8-yl]cyclohexanecarboxamide
schembl18188080
cdk9 inhibitor
(s)-selisistat
parthenolide;c/c/1=c\cc[c@@]2([c@h](o2)[c@@h]3[c@@h](cc1)c(=c)c(=o)o3)c
marinopyrrole a
brd-a34462049-001-01-0
etp-46464
lsm-6185
bx-795
nu-7441
n-[(2s,3s,6r)-2-(hydroxymethyl)-6-[2-(4-methyl-1-piperazinyl)-2-oxoethyl]-3-oxanyl]-1,3-benzodioxole-5-carboxamide
xhqlywyicdktpj-uhfffaoysa-n
cay10603
nelarabine
parbendazole
brd-k33199242-001-01-2
mln2480
lsm-13729
tubastatin a
kpt-185
bai1
ci 976
importazole
brd-k04800985-001-01-1
gw 441756
schembl16273428
mitomycin c
i-bet151
as-605240
pd318088
cil56
brd-k02492147-001-01-4
azd1152-hqpa
brd-k27986637-001-01-3
ethyl 2-cyano-3-(3,4-dichlorophenyl)acryloylcarbamate
tcmdc-125552
bms-345541;cc1=cc2=c(c=c1)n=c(c3=nc=c(n23)c)nccn
bay 61-3606 + hydrochloric acid
bryostatin 1
bam7
palmostatin b
serdemetan
jq1 + unc0638
n-[2-methyl-5-[oxo-[3-(1-oxoprop-2-enylamino)-5-(trifluoromethyl)anilino]methyl]phenyl]-5-isoxazolecarboxamide
oprea1_718426
tipifarnib (s enantiomer)
salermide
sch-529074
pf-543
sb-525334
ro-3306
pf-4708671
gsk461364
pf 184
lrlwxbhfpgsuox-hhkxydnmsa-n
bendamustine
chembl416418
pik-93
chembl568305
chembl3188232
ku-55933
6-bio
ku-60019
schembl16296919
ak174031 + mk-1775
ml311
schembl18426910
vaf347
bms-536924;cc1=cc(=cc2=c1nc(=c3c(=cc=nc3=o)nc[c@h](c4=cc(=cc=c4)cl)o)n2)n5ccocc5
sl-0101
mps1-in-1 + hydrochloric acid
nsc 95397
lfm-a13
schembl16046542
telomerase inhibitor ix
mls000106215
procarbazine
gnf-2
fqi1
brd-a28105619-001-01-3
ly2183240
embelin
mtlmdzjugdutcp-ywefrbeisa-n
cot inhibitor-2
isoliquiritigenin
n-[3-[[2-[[4-(dimethylamino)cyclohexyl]amino]-9-propan-2-yl-6-purinyl]amino]phenyl]-2-propenamide
bms270394
nsc74859
austocystin d
schembl15428380
ku-0060648
dasa-58
n-[(2r,3s)-5-[(2r)-1-hydroxypropan-2-yl]-3-methyl-2-(methylaminomethyl)-6-oxo-2,3,4,7-tetrahydro-1,5-benzoxazonin-9-yl]-3-(4-morpholinyl)propanamide
brd-a59431241-001-01-1
whi-p97
brd-a15100685-001-01-8
schembl4463213
osi-027;coc1=cc=cc2=c/c(=c/3\c4=c(n=cnn4c(=n3)c5ccc(cc5)c(=o)o)n)/n=c21
aica ribonucleotide
n-[(2s,3s)-2-[[[(cyclohexylamino)-oxomethyl]-methylamino]methyl]-5-[(2r)-1-hydroxypropan-2-yl]-3-methyl-6-oxo-3,4-dihydro-2h-1,5-benzoxazocin-8-yl]-2-(1-methyl-3-indolyl)acetamide
chs-828
ifosfamide
sepantronium + bromide
bleomycin sulfate
gsk1904529a
ouabain
n-[(2r,3s)-2-[[(4-chlorophenyl)sulfonyl-methylamino]methyl]-5-[(2s)-1-hydroxypropan-2-yl]-3-methyl-6-oxo-2,3,4,7-tetrahydro-1,5-benzoxazonin-9-yl]-4,4,4-trifluorobutanamide
1009820-21-6
azanide; dichloroplatinum(2+)
brd3308
leptomycin b
as601245
erk5-in-1
phenformin
rg108
at7867
chebi:93385
tcmdc-123515
stf-31
chembl2062550
n-[2-methyl-5-[2-oxo-9-(1h-pyrazol-4-yl)-1-benzo[h][1,6]naphthyridinyl]phenyl]-2-propenamide
brd-k16147474-001-01-1
ubrvgbldxdoetm-uhfffaoysa-n
qfjcirlumzquot-laoshscvsa-n
ml-210
necrosulfonamide
a-804598
schembl15422028
schembl14934014
cdk4/6 inhibitor iv
srlvtmsbrcmody-qxpfvdmisa-n
j3.559.058g
tgx-221
gw2580
schembl6465274
nsc136476
c646
mls001198989
hms1361j12
ciclopirox
schembl10183194
salubrinal
ko 143
z-llnle-cho
lsm-6189
temozolomide
chembl258148
n-(4-methoxyphenyl)sulfonyl-n-[2-[2-(1-oxido-4-pyridin-1-iumyl)ethenyl]phenyl]acetamide
necrostatin-1
n'-[(6-oxo-5-prop-2-enyl-1-cyclohexa-2,4-dienylidene)methyl]-2-[4-(phenylmethyl)-1-piperazinyl]acetohydrazide;c=ccc1=cc=cc(=cnnc(=o)cn2ccn(cc2)cc3=cc=cc=c3)c1=o
nsc48300
lrrk2-in-1
t0901317
n-cyclopropyl-3-[3-[[cyclopropyl(oxo)methyl]amino]-1h-indazol-6-yl]benzamide
jw-55
pf-4800567
az-628
fr-180204
wz4002
schembl12182311
brd4770
brd-k41597374-001-01-7
eht-1864
n'-[(6-oxo-5-prop-2-enyl-1-cyclohexa-2,4-dienylidene)methyl]-2-[4-(phenylmethyl)-1-piperazinyl]acetohydrazide;c=ccc1=cc=c/c(=c/nnc(=o)cn2ccn(cc2)cc3=cc=cc=c3)/c1=o
wz8040
ahpn
chembl2152368
epz004777 + schembl2671349
nan + nan
schembl4320913
lsm-36779
brd-k29086754-001-01-7
a-443654
sepantronium
isoevodiamine
retinol + schembl2671349
sch-529074 + jnj-26854165
agwauacrbaqpjj-uhfffaoysa-n
chembl520231
schembl11942935
chembl3185999
n-methyl-n-[4-[[6-[[1-(1-oxoprop-2-enyl)-3-piperidinyl]amino]-7h-purin-2-yl]amino]phenyl]propanamide
parthenolide;c/c/1=c/cc[c@@]2([c@h](o2)[c@@h]3[c@@h](cc1)c(=c)c(=o)o3)c
ym-201636
schembl2671349
smr000198998
rigosertib
dqnfqthsdkxsee-qfzqxzrasa-n
cbb1007
oqhlpaawwgdxaw-uhfffaoysa-n
daporinad
cyclophosphamide
mi-1
schembl12041987
chembl2206358
brd-1240
isonicotinohydroxamic acid
rsl3
schembl13833318
1,2-cyclohexanediamine anion + oxalic acid
sb-216763
brd-k05870596-001-01-4
dnmdp-2
n-[6-(2-amino-4-fluoroanilino)-6-oxohexyl]-4-methylbenzamide
chembl2398212
akt inhibitor viii

Study drug with unknown MOA

Choose drug with unknown MOA…

combobox_u = interactive(f, drug=widgets.Combobox(options=unknown))

predictions_nodes = []
for goterm in list(platt_matrix.index):
    predictions_nodes.append(goterm+"_"+str(1))

# add names to go terms
real_go_info_svm= real_go_info[real_go_info.GO_term.isin(predictions_nodes)]
real_go_info_svm.GO_term = real_go_info_svm.GO_term.str.replace("_1","")

display(combobox_u)

selected_drug_u_name = combobox_u.result

predictions_df = pd.DataFrame.from_dict(preds_unknown.loc[:,selected_drug_u_name]).reset_index()
predictions_df.columns  = ["GO_term","predictions"]

probabilities_df = pd.DataFrame.from_dict(probabilities_unknown.loc[:,selected_drug_u_name]).reset_index()
probabilities_df.columns  = ["GO_term","probability"]
probabilities_df = probabilities_df.merge(real_go_info_svm, on="GO_term")
probabilities_df = probabilities_df.merge(predictions_df, on="GO_term")
probabilities_df.loc[probabilities_df["layer_number"] <=3].sort_values(by=["probability"], ascending=False).head(200)

	GO_term	probability	Name	layer_number	predictions
820	GO:0033993	0.809556	Response to lipid (1)	3.0	1.0
223	GO:0018108	0.783375	Peptidyl-tyrosine phosphorylation (1)	3.0	1.0
573	GO:0010629	0.742615	Negative regulation of gene expression (1)	3.0	1.0
106	GO:0071900	0.725062	Regulation of protein serine/threonine kinase activity (1)	2.0	1.0
624	GO:0010628	0.702924	Positive regulation of gene expression (1)	3.0	1.0
74	GO:0001817	0.687600	Regulation of cytokine production (1)	3.0	1.0
44	GO:0048812	0.672129	Neuron projection morphogenesis (1)	3.0	1.0
224	GO:0046777	0.661031	Protein autophosphorylation (1)	1.0	1.0
99	GO:0001934	0.658374	Positive regulation of protein phosphorylation (1)	3.0	1.0
570	GO:0045597	0.628072	Positive regulation of cell differentiation (1)	3.0	1.0
839	GO:0031047	0.553888	Gene silencing by rna (1)	2.0	1.0
100	GO:0033138	0.542770	Positive regulation of peptidyl-serine phosphorylation (1)	1.0	1.0
888	GO:0034976	0.540483	Response to endoplasmic reticulum stress (1)	3.0	1.0
633	GO:0051301	0.535293	Cell division (1)	2.0	1.0
821	GO:0034097	0.533600	Response to cytokine (1)	3.0	1.0
423	GO:1902533	0.530199	Positive regulation of intracellular signal transduction (1)	2.0	1.0
596	GO:0060341	0.523390	Regulation of cellular localization (1)	3.0	0.0
729	GO:0120035	0.514954	Regulation of plasma membrane bounded cell projection organization (1)	3.0	1.0
568	GO:0008284	0.513916	Positive regulation of cell population proliferation (1)	2.0	1.0
558	GO:0016032	0.500000	Viral process (1)	3.0	1.0
641	GO:0071417	0.494543	Cellular response to organonitrogen compound (1)	3.0	1.0
353	GO:0006954	0.482633	Inflammatory response (1)	3.0	1.0
9	GO:0043408	0.476159	Regulation of mapk cascade (1)	2.0	1.0
808	GO:1902532	0.449154	Negative regulation of intracellular signal transduction (1)	3.0	1.0
11	GO:0043406	0.445845	Positive regulation of map kinase activity (1)	1.0	1.0
8	GO:0000165	0.443783	Mapk cascade (1)	3.0	0.0
358	GO:0007005	0.427023	Mitochondrion organization (1)	3.0	1.0
134	GO:0002366	0.423235	Leukocyte activation involved in immune response (1)	3.0	1.0
221	GO:0018105	0.422261	Peptidyl-serine phosphorylation (1)	2.0	0.0
285	GO:0051051	0.421500	Negative regulation of transport (1)	3.0	1.0
191	GO:0045944	0.420524	Positive regulation of transcription by rna polymerase ii (1)	2.0	1.0
654	GO:0090398	0.416328	Cellular senescence (1)	1.0	1.0
847	GO:0045055	0.414665	Regulated exocytosis (1)	2.0	1.0
342	GO:2001243	0.411574	Negative regulation of intrinsic apoptotic signaling pathway (1)	2.0	1.0
510	GO:0042063	0.408279	Gliogenesis (1)	3.0	1.0
788	GO:0009410	0.407937	Response to xenobiotic stimulus (1)	2.0	1.0
824	GO:0071363	0.407544	Cellular response to growth factor stimulus (1)	3.0	1.0
496	GO:0048608	0.406699	Reproductive structure development (1)	2.0	1.0
528	GO:0007565	0.406022	Female pregnancy (1)	2.0	1.0
896	GO:0097193	0.400210	Intrinsic apoptotic signaling pathway (1)	3.0	1.0
76	GO:0001819	0.388417	Positive regulation of cytokine production (1)	2.0	1.0
48	GO:0001525	0.386728	Angiogenesis (1)	2.0	1.0
300	GO:0032386	0.384834	Regulation of intracellular transport (1)	2.0	1.0
906	GO:0043549	0.378711	Regulation of kinase activity (1)	3.0	0.0
662	GO:0031648	0.377411	Protein destabilization (1)	0.0	1.0
516	GO:0007423	0.372363	Sensory organ development (1)	3.0	1.0
461	GO:0050804	0.367884	Modulation of chemical synaptic transmission (1)	3.0	1.0
104	GO:0006469	0.364467	Negative regulation of protein kinase activity (1)	2.0	1.0
620	GO:0051098	0.363823	Regulation of binding (1)	3.0	1.0
86	GO:0072006	0.358531	Nephron development (1)	2.0	1.0
473	GO:0008584	0.350294	Male gonad development (1)	1.0	1.0
536	GO:0007610	0.346612	Behavior (1)	3.0	0.0
693	GO:1904646	0.344997	Cellular response to amyloid-beta (1)	0.0	1.0
376	GO:0007015	0.344878	Actin filament organization (1)	3.0	1.0
552	GO:0033365	0.343027	Protein localization to organelle (1)	3.0	1.0
774	GO:0030216	0.342203	Keratinocyte differentiation (1)	2.0	1.0
639	GO:0060326	0.341919	Cell chemotaxis (1)	2.0	1.0
154	GO:0050778	0.335649	Positive regulation of immune response (1)	3.0	0.0
480	GO:0048565	0.333289	Digestive tract development (1)	1.0	1.0
794	GO:0043434	0.332497	Response to peptide hormone (1)	3.0	1.0
651	GO:0050808	0.322913	Synapse organization (1)	3.0	1.0
772	GO:0060485	0.320964	Mesenchyme development (1)	3.0	1.0
406	GO:0048041	0.319689	Focal adhesion assembly (1)	1.0	1.0
698	GO:0070663	0.318299	Regulation of leukocyte proliferation (1)	2.0	1.0
804	GO:0030855	0.317904	Epithelial cell differentiation (1)	3.0	0.0
538	GO:0048266	0.308838	Behavioral response to pain (1)	0.0	1.0
225	GO:0006470	0.305848	Protein dephosphorylation (1)	3.0	1.0
719	GO:0043244	0.305739	Regulation of protein-containing complex disassembly (1)	2.0	1.0
725	GO:0070997	0.305130	Neuron death (1)	2.0	0.0
532	GO:0007596	0.304871	Blood coagulation (1)	3.0	1.0
806	GO:0051056	0.302828	Regulation of small gtpase mediated signal transduction (1)	3.0	1.0
433	GO:0097191	0.302625	Extrinsic apoptotic signaling pathway (1)	3.0	1.0
574	GO:0008285	0.300631	Negative regulation of cell population proliferation (1)	3.0	0.0
49	GO:0001569	0.300115	Branching involved in blood vessel morphogenesis (1)	0.0	1.0
926	GO:0060020	0.297104	Bergmann glial cell differentiation (1)	0.0	1.0
789	GO:0009416	0.295539	Response to light stimulus (1)	2.0	0.0
887	GO:0034504	0.294393	Protein localization to nucleus (1)	2.0	1.0
169	GO:0002764	0.292841	Immune response-regulating signaling pathway (1)	3.0	0.0
890	GO:0071353	0.290912	Cellular response to interleukin-4 (1)	1.0	1.0
505	GO:0007283	0.290337	Spermatogenesis (1)	2.0	1.0
513	GO:0030900	0.289030	Forebrain development (1)	3.0	1.0
241	GO:0006612	0.288796	Protein targeting to membrane (1)	1.0	1.0
644	GO:0071230	0.284292	Cellular response to amino acid stimulus (1)	1.0	1.0
712	GO:0033002	0.280632	Muscle cell proliferation (1)	2.0	1.0
317	GO:0006897	0.277768	Endocytosis (1)	3.0	1.0
230	GO:0030162	0.277751	Regulation of proteolysis (1)	3.0	0.0
607	GO:0042391	0.276380	Regulation of membrane potential (1)	3.0	0.0
689	GO:1905897	0.275961	Regulation of response to endoplasmic reticulum stress (1)	2.0	1.0
105	GO:0045860	0.275729	Positive regulation of protein kinase activity (1)	2.0	0.0
198	GO:0006260	0.275261	Dna replication (1)	3.0	1.0
548	GO:1903829	0.274893	Positive regulation of protein localization (1)	3.0	0.0
934	GO:0051258	0.274092	Protein polymerization (1)	3.0	1.0
378	GO:0031532	0.271109	Actin cytoskeleton reorganization (1)	1.0	1.0
216	GO:0045727	0.270882	Positive regulation of translation (1)	1.0	1.0
642	GO:0034599	0.270088	Cellular response to oxidative stress (1)	3.0	0.0
767	GO:0051146	0.266722	Striated muscle cell differentiation (1)	2.0	0.0
77	GO:0002718	0.262195	Regulation of cytokine production involved in immune response (1)	2.0	1.0
19	GO:0031109	0.261030	Microtubule polymerization or depolymerization (1)	2.0	1.0
584	GO:0040008	0.259597	Regulation of growth (1)	3.0	0.0
937	GO:0051640	0.257672	Organelle localization (1)	3.0	0.0
377	GO:0031032	0.257340	Actomyosin structure organization (1)	2.0	1.0
904	GO:0042113	0.254618	B cell activation (1)	3.0	0.0
133	GO:0043303	0.253768	Mast cell degranulation (1)	1.0	1.0
561	GO:0048511	0.251652	Rhythmic process (1)	3.0	1.0
243	GO:0006606	0.250144	Protein import into nucleus (1)	1.0	1.0
836	GO:1901987	0.249107	Regulation of cell cycle phase transition (1)	3.0	0.0
758	GO:0031099	0.247922	Regeneration (1)	2.0	1.0
739	GO:1902903	0.245529	Regulation of supramolecular fiber organization (1)	3.0	1.0
323	GO:0016236	0.245469	Macroautophagy (1)	3.0	1.0
478	GO:0048568	0.244894	Embryonic organ development (1)	3.0	0.0
103	GO:0042531	0.243583	Positive regulation of tyrosine phosphorylation of stat protein (1)	0.0	1.0
598	GO:0043254	0.240098	Regulation of protein-containing complex assembly (1)	3.0	1.0
864	GO:0030183	0.236405	B cell differentiation (1)	1.0	0.0
301	GO:0032388	0.235842	Positive regulation of intracellular transport (1)	1.0	0.0
692	GO:0010595	0.235403	Positive regulation of endothelial cell migration (1)	2.0	1.0
865	GO:0030217	0.234830	T cell differentiation (1)	3.0	0.0
20	GO:0070507	0.234661	Regulation of microtubule cytoskeleton organization (1)	2.0	1.0
111	GO:0031069	0.234249	Hair follicle morphogenesis (1)	0.0	1.0
363	GO:0051494	0.232679	Negative regulation of cytoskeleton organization (1)	2.0	1.0
226	GO:0035304	0.232643	Regulation of protein dephosphorylation (1)	2.0	1.0
913	GO:0090630	0.231968	Activation of gtpase activity (1)	0.0	1.0
733	GO:0030335	0.231192	Positive regulation of cell migration (1)	3.0	0.0
196	GO:0006357	0.230696	Regulation of transcription by rna polymerase ii (1)	3.0	1.0
524	GO:0007519	0.230417	Skeletal muscle tissue development (1)	2.0	1.0
53	GO:0001570	0.230416	Vasculogenesis (1)	1.0	1.0
26	GO:1901990	0.229708	Regulation of mitotic cell cycle phase transition (1)	2.0	0.0
33	GO:0000423	0.229518	Mitophagy (1)	1.0	1.0
615	GO:0035265	0.227576	Organ growth (1)	2.0	0.0
84	GO:0001822	0.227091	Kidney development (1)	3.0	0.0
151	GO:0006959	0.225795	Humoral immune response (1)	2.0	1.0
244	GO:0042307	0.225164	Positive regulation of protein import into nucleus (1)	0.0	1.0
24	GO:0007346	0.224934	Regulation of mitotic cell cycle (1)	3.0	0.0
162	GO:0060374	0.223666	Mast cell differentiation (1)	0.0	1.0
533	GO:0030168	0.219923	Platelet activation (1)	2.0	1.0
152	GO:0045087	0.218376	Innate immune response (1)	3.0	0.0
523	GO:0007517	0.217930	Muscle organ development (1)	3.0	0.0
138	GO:0002683	0.217495	Negative regulation of immune system process (1)	3.0	0.0
319	GO:0006909	0.217477	Phagocytosis (1)	2.0	1.0
18	GO:0000226	0.216530	Microtubule cytoskeleton organization (1)	3.0	0.0
622	GO:0043086	0.212387	Negative regulation of catalytic activity (1)	3.0	1.0
898	GO:0035924	0.211788	Cellular response to vascular endothelial growth factor stimulus (1)	2.0	1.0
187	GO:0071897	0.211315	Dna biosynthetic process (1)	2.0	0.0
517	GO:0043586	0.209986	Tongue development (1)	1.0	1.0
606	GO:0048638	0.209981	Regulation of developmental growth (1)	2.0	0.0
736	GO:0009617	0.209127	Response to bacterium (1)	3.0	0.0
691	GO:0043542	0.207450	Endothelial cell migration (1)	3.0	0.0
321	GO:0010507	0.205494	Negative regulation of autophagy (1)	1.0	1.0
149	GO:0050853	0.205417	B cell receptor signaling pathway (1)	1.0	0.0
885	GO:1900180	0.205300	Regulation of protein localization to nucleus (1)	1.0	1.0
907	GO:0051881	0.202707	Regulation of mitochondrial membrane potential (1)	1.0	0.0
171	GO:0003014	0.201637	Renal system process (1)	2.0	1.0
211	GO:0031507	0.200984	Heterochromatin assembly (1)	1.0	1.0
64	GO:0071456	0.200564	Cellular response to hypoxia (1)	1.0	0.0
694	GO:0032869	0.197755	Cellular response to insulin stimulus (1)	2.0	0.0
779	GO:0008544	0.196206	Epidermis development (1)	3.0	0.0
634	GO:0061024	0.193065	Membrane organization (1)	2.0	0.0
50	GO:0002040	0.192737	Sprouting angiogenesis (1)	1.0	0.0
610	GO:0031333	0.191284	Negative regulation of protein-containing complex assembly (1)	2.0	1.0
657	GO:0045165	0.191259	Cell fate commitment (1)	3.0	0.0
435	GO:0016055	0.190638	Wnt signaling pathway (1)	2.0	0.0
569	GO:0030307	0.190101	Positive regulation of cell growth (1)	2.0	1.0
200	GO:0006281	0.189187	Dna repair (1)	2.0	0.0
63	GO:0001666	0.188575	Response to hypoxia (1)	2.0	1.0
560	GO:0043473	0.188137	Pigmentation (1)	2.0	1.0
521	GO:0035051	0.187551	Cardiocyte differentiation (1)	2.0	1.0
690	GO:2001020	0.187450	Regulation of response to dna damage stimulus (1)	2.0	0.0
346	GO:0006936	0.187431	Muscle contraction (1)	3.0	1.0
328	GO:0043065	0.184805	Positive regulation of apoptotic process (1)	2.0	0.0
650	GO:0034329	0.183554	Cell junction assembly (1)	2.0	0.0
262	GO:0045429	0.183059	Positive regulation of nitric oxide biosynthetic process (1)	0.0	1.0
117	GO:0060562	0.183024	Epithelial tube morphogenesis (1)	2.0	0.0
583	GO:0032967	0.182852	Positive regulation of collagen biosynthetic process (1)	0.0	1.0
208	GO:0006325	0.182003	Chromatin organization (1)	3.0	0.0
209	GO:0006338	0.181855	Chromatin remodeling (1)	2.0	1.0
882	GO:0032147	0.181843	Activation of protein kinase activity (1)	1.0	0.0
7	GO:0000122	0.181449	Negative regulation of transcription by rna polymerase ii (1)	1.0	0.0
911	GO:0060416	0.180831	Response to growth hormone (1)	1.0	1.0
121	GO:0090050	0.180206	Positive regulation of cell migration involved in sprouting angiogenesis (1)	0.0	1.0
467	GO:0009791	0.179613	Post-embryonic development (1)	1.0	0.0
870	GO:0070527	0.179383	Platelet aggregation (1)	1.0	1.0
781	GO:0008625	0.179216	Extrinsic apoptotic signaling pathway via death domain receptors (1)	1.0	1.0
702	GO:0048146	0.179210	Positive regulation of fibroblast proliferation (1)	0.0	1.0
785	GO:0009266	0.178944	Response to temperature stimulus (1)	2.0	1.0
316	GO:0033157	0.178583	Regulation of intracellular protein transport (1)	1.0	0.0
472	GO:0001553	0.178541	Luteinization (1)	0.0	1.0
174	GO:0010613	0.176998	Positive regulation of cardiac muscle hypertrophy (1)	1.0	1.0
842	GO:0071407	0.176595	Cellular response to organic cyclic compound (1)	3.0	0.0
834	GO:0035195	0.176389	Gene silencing by mirna (1)	1.0	0.0
504	GO:0048709	0.176248	Oligodendrocyte differentiation (1)	2.0	1.0
54	GO:2001214	0.175971	Positive regulation of vasculogenesis (1)	0.0	1.0
600	GO:0010632	0.174413	Regulation of epithelial cell migration (1)	3.0	0.0
682	GO:0007026	0.174040	Negative regulation of microtubule depolymerization (1)	0.0	1.0
276	GO:0016567	0.173194	Protein ubiquitination (1)	3.0	0.0
881	GO:0031929	0.171840	Tor signaling (1)	2.0	1.0
52	GO:0001541	0.171713	Ovarian follicle development (1)	1.0	0.0
310	GO:0051924	0.171261	Regulation of calcium ion transport (1)	3.0	0.0
899	GO:0035994	0.170901	Response to muscle stretch (1)	1.0	1.0
32	GO:0000422	0.170612	Autophagy of mitochondrion (1)	2.0	1.0
703	GO:0048661	0.169791	Positive regulation of smooth muscle cell proliferation (1)	1.0	0.0
447	GO:0007173	0.169218	Epidermal growth factor receptor signaling pathway (1)	2.0	0.0

sum(probabilities_df["predictions"] ==1)

288

sum(probabilities_df["predictions"] ==0)

651

Probability < 0.5 doesn’t mean it does not belong to the class, a probability of for example 0.2 can represent a 1 (annotated to MoA)

Modify probabilities

Take into account the annotations each GO term has (general GO terms are easier to predict as they have more annotations)

For drug with unknown MOA…

sum_annotations = slim_matrix_single_neuron.T.sum()/slim_matrix_single_neuron.shape[1]
logits_apriori = np.log(sum_annotations/(1-sum_annotations))

logits_apost= np.log(probabilities_df["probability"]/(1-probabilities_df["probability"]))
delta_logits =logits_apost.to_numpy()- logits_apriori.to_numpy()
delta_logits_df = pd.DataFrame(delta_logits)
delta_logits_df.columns = ["delta_logits"]
probabilities_mod = probabilities_df.merge(delta_logits_df, left_index=True,right_index=True)

probabilities_mod.loc[probabilities_mod["predictions"] ==1].loc[probabilities_mod["layer_number"] <= 7].sort_values(by=["delta_logits"], ascending=False)

	GO_term	probability	Name	layer_number	predictions	delta_logits
839	GO:0031047	0.553888	Gene silencing by rna (1)	2.0	1.0	2.192458
662	GO:0031648	0.377411	Protein destabilization (1)	0.0	1.0	2.092834
106	GO:0071900	0.725062	Regulation of protein serine/threonine kinase activity (1)	2.0	1.0	1.944569
33	GO:0000423	0.229518	Mitophagy (1)	1.0	1.0	1.880007
538	GO:0048266	0.308838	Behavioral response to pain (1)	0.0	1.0	1.857031
913	GO:0090630	0.231968	Activation of gtpase activity (1)	0.0	1.0	1.793943
216	GO:0045727	0.270882	Positive regulation of translation (1)	1.0	1.0	1.746070
223	GO:0018108	0.783375	Peptidyl-tyrosine phosphorylation (1)	3.0	1.0	1.672826
719	GO:0043244	0.305739	Regulation of protein-containing complex disassembly (1)	2.0	1.0	1.646098
241	GO:0006612	0.288796	Protein targeting to membrane (1)	1.0	1.0	1.626841
104	GO:0006469	0.364467	Negative regulation of protein kinase activity (1)	2.0	1.0	1.593794
888	GO:0034976	0.540483	Response to endoplasmic reticulum stress (1)	3.0	1.0	1.575980
890	GO:0071353	0.290912	Cellular response to interleukin-4 (1)	1.0	1.0	1.575256
638	GO:0033554	0.884331	Cellular response to stress (1)	4.0	1.0	1.573975
820	GO:0033993	0.809556	Response to lipid (1)	3.0	1.0	1.551573
74	GO:0001817	0.687600	Regulation of cytokine production (1)	3.0	1.0	1.534715
682	GO:0007026	0.174040	Negative regulation of microtubule depolymerization (1)	0.0	1.0	1.533781
528	GO:0007565	0.406022	Female pregnancy (1)	2.0	1.0	1.478881
224	GO:0046777	0.661031	Protein autophosphorylation (1)	1.0	1.0	1.453821
544	GO:0060179	0.161090	Male mating behavior (1)	0.0	1.0	1.440901
32	GO:0000422	0.170612	Autophagy of mitochondrion (1)	2.0	1.0	1.409881
774	GO:0030216	0.342203	Keratinocyte differentiation (1)	2.0	1.0	1.406530
44	GO:0048812	0.672129	Neuron projection morphogenesis (1)	3.0	1.0	1.385004
472	GO:0001553	0.178541	Luteinization (1)	0.0	1.0	1.373326
77	GO:0002718	0.262195	Regulation of cytokine production involved in immune response (1)	2.0	1.0	1.372827
900	GO:0042060	0.612497	Wound healing (1)	4.0	1.0	1.325911
385	GO:0060632	0.143694	Regulation of microtubule-based movement (1)	1.0	1.0	1.306104
726	GO:0065003	0.654123	Protein-containing complex assembly (1)	4.0	1.0	1.304384
926	GO:0060020	0.297104	Bergmann glial cell differentiation (1)	0.0	1.0	1.288696
582	GO:1902459	0.140358	Positive regulation of stem cell population maintenance (1)	0.0	1.0	1.278722
63	GO:0001666	0.188575	Response to hypoxia (1)	2.0	1.0	1.276928
342	GO:2001243	0.411574	Negative regulation of intrinsic apoptotic signaling pathway (1)	2.0	1.0	1.262448
573	GO:0010629	0.742615	Negative regulation of gene expression (1)	3.0	1.0	1.216446
480	GO:0048565	0.333289	Digestive tract development (1)	1.0	1.0	1.203775
174	GO:0010613	0.176998	Positive regulation of cardiac muscle hypertrophy (1)	1.0	1.0	1.199403
676	GO:0030282	0.116755	Bone mineralization (1)	1.0	1.0	1.177409
49	GO:0001569	0.300115	Branching involved in blood vessel morphogenesis (1)	0.0	1.0	1.170620
899	GO:0035994	0.170901	Response to muscle stretch (1)	1.0	1.0	1.156962
443	GO:0035860	0.114067	Glial cell-derived neurotrophic factor receptor signaling pathway (1)	0.0	1.0	1.151083
847	GO:0045055	0.414665	Regulated exocytosis (1)	2.0	1.0	1.096844
134	GO:0002366	0.423235	Leukocyte activation involved in immune response (1)	3.0	1.0	1.076788
181	GO:0006139	0.875555	Nucleobase-containing compound metabolic process (1)	6.0	1.0	1.061941
689	GO:1905897	0.275961	Regulation of response to endoplasmic reticulum stress (1)	2.0	1.0	1.052784
38	GO:0000902	0.813929	Cell morphogenesis (1)	4.0	1.0	1.052132
654	GO:0090398	0.416328	Cellular senescence (1)	1.0	1.0	1.048427
693	GO:1904646	0.344997	Cellular response to amyloid-beta (1)	0.0	1.0	1.043235
100	GO:0033138	0.542770	Positive regulation of peptidyl-serine phosphorylation (1)	1.0	1.0	1.018799
745	GO:0009653	0.877370	Anatomical structure morphogenesis (1)	5.0	1.0	1.014649
198	GO:0006260	0.275261	Dna replication (1)	3.0	1.0	1.007970
133	GO:0043303	0.253768	Mast cell degranulation (1)	1.0	1.0	0.981406
368	GO:0060271	0.126831	Cilium assembly (1)	3.0	1.0	0.970313
285	GO:0051051	0.421500	Negative regulation of transport (1)	3.0	1.0	0.964316
626	GO:0051649	0.802013	Establishment of localization in cell (1)	4.0	1.0	0.957089
378	GO:0031532	0.271109	Actin cytoskeleton reorganization (1)	1.0	1.0	0.947004
651	GO:0050808	0.322913	Synapse organization (1)	3.0	1.0	0.943923
11	GO:0043406	0.445845	Positive regulation of map kinase activity (1)	1.0	1.0	0.939978
34	GO:1903146	0.103490	Regulation of autophagy of mitochondrion (1)	1.0	1.0	0.932003
262	GO:0045429	0.183059	Positive regulation of nitric oxide biosynthetic process (1)	0.0	1.0	0.911660
661	GO:0046326	0.165116	Positive regulation of glucose import (1)	0.0	1.0	0.907432
911	GO:0060416	0.180831	Response to growth hormone (1)	1.0	1.0	0.896690
571	GO:2000010	0.127151	Positive regulation of protein localization to cell surface (1)	0.0	1.0	0.888565
633	GO:0051301	0.535293	Cell division (1)	2.0	1.0	0.887200
483	GO:0035909	0.162013	Aorta morphogenesis (1)	1.0	1.0	0.884752
54	GO:2001214	0.175971	Positive regulation of vasculogenesis (1)	0.0	1.0	0.863534
416	GO:0035556	0.887824	Intracellular signal transduction (1)	4.0	1.0	0.862843
470	GO:0042733	0.097137	Embryonic digit morphogenesis (1)	0.0	1.0	0.861598
886	GO:0034502	0.132453	Protein localization to chromosome (1)	2.0	1.0	0.856780
111	GO:0031069	0.234249	Hair follicle morphogenesis (1)	0.0	1.0	0.832897
880	GO:0031667	0.374380	Response to nutrient levels (1)	4.0	1.0	0.819334
833	GO:0010467	0.880677	Gene expression (1)	5.0	1.0	0.817357
184	GO:0006275	0.102018	Regulation of dna replication (1)	2.0	1.0	0.816174
162	GO:0060374	0.223666	Mast cell differentiation (1)	0.0	1.0	0.815593
265	GO:0051247	0.818839	Positive regulation of protein metabolic process (1)	4.0	1.0	0.802282
821	GO:0034097	0.533600	Response to cytokine (1)	3.0	1.0	0.801775
408	GO:0007165	0.930074	Signal transduction (1)	6.0	1.0	0.801131
849	GO:0043966	0.142338	Histone h3 acetylation (1)	2.0	1.0	0.797379
112	GO:0060789	0.091132	Hair follicle placode formation (1)	0.0	1.0	0.791156
558	GO:0016032	0.500000	Viral process (1)	3.0	1.0	0.785929
151	GO:0006959	0.225795	Humoral immune response (1)	2.0	1.0	0.785159
86	GO:0072006	0.358531	Nephron development (1)	2.0	1.0	0.777591
83	GO:0002720	0.163684	Positive regulation of cytokine production involved in immune response (1)	1.0	1.0	0.776348
53	GO:0001570	0.230416	Vasculogenesis (1)	1.0	1.0	0.770097
532	GO:0007596	0.304871	Blood coagulation (1)	3.0	1.0	0.764501
567	GO:0051641	0.841801	Cellular localization (1)	5.0	1.0	0.761481
639	GO:0060326	0.341919	Cell chemotaxis (1)	2.0	1.0	0.758938
19	GO:0031109	0.261030	Microtubule polymerization or depolymerization (1)	2.0	1.0	0.746075
800	GO:0030521	0.102431	Androgen receptor signaling pathway (1)	1.0	1.0	0.729092
511	GO:0030182	0.721830	Neuron differentiation (1)	5.0	1.0	0.726501
806	GO:0051056	0.302828	Regulation of small gtpase mediated signal transduction (1)	3.0	1.0	0.724275
527	GO:0007528	0.109807	Neuromuscular junction development (1)	1.0	1.0	0.722229
794	GO:0043434	0.332497	Response to peptide hormone (1)	3.0	1.0	0.716778
99	GO:0001934	0.658374	Positive regulation of protein phosphorylation (1)	3.0	1.0	0.708241
896	GO:0097193	0.400210	Intrinsic apoptotic signaling pathway (1)	3.0	1.0	0.705651
624	GO:0010628	0.702924	Positive regulation of gene expression (1)	3.0	1.0	0.704419
722	GO:0042325	0.780828	Regulation of phosphorylation (1)	5.0	1.0	0.698909
752	GO:0043170	0.942545	Macromolecule metabolic process (1)	7.0	1.0	0.693446
517	GO:0043586	0.209986	Tongue development (1)	1.0	1.0	0.692360
182	GO:0016070	0.778891	Rna metabolic process (1)	5.0	1.0	0.687621
281	GO:0006811	0.500000	Ion transport (1)	6.0	1.0	0.686632
586	GO:2000773	0.121640	Negative regulation of cellular senescence (1)	0.0	1.0	0.685597
808	GO:1902532	0.449154	Negative regulation of intracellular signal transduction (1)	3.0	1.0	0.684968
570	GO:0045597	0.628072	Positive regulation of cell differentiation (1)	3.0	1.0	0.680798
76	GO:0001819	0.388417	Positive regulation of cytokine production (1)	2.0	1.0	0.679733
934	GO:0051258	0.274092	Protein polymerization (1)	3.0	1.0	0.677814
713	GO:0035726	0.096936	Common myeloid progenitor cell proliferation (1)	0.0	1.0	0.667842
386	GO:0007049	0.727375	Cell cycle (1)	6.0	1.0	0.665704
473	GO:0008584	0.350294	Male gonad development (1)	1.0	1.0	0.663186
813	GO:0051898	0.103239	Negative regulation of protein kinase b signaling (1)	0.0	1.0	0.653209
698	GO:0070663	0.318299	Regulation of leukocyte proliferation (1)	2.0	1.0	0.652091
729	GO:0120035	0.514954	Regulation of plasma membrane bounded cell projection organization (1)	3.0	1.0	0.631426
881	GO:0031929	0.171840	Tor signaling (1)	2.0	1.0	0.624585
496	GO:0048608	0.406699	Reproductive structure development (1)	2.0	1.0	0.619202
559	GO:0022414	0.641754	Reproductive process (1)	4.0	1.0	0.617772
562	GO:0050896	0.963328	Response to stimulus (1)	7.0	1.0	0.605804
381	GO:0008064	0.113103	Regulation of actin polymerization or depolymerization (1)	2.0	1.0	0.603158
855	GO:1903578	0.141298	Regulation of atp metabolic process (1)	1.0	1.0	0.602865
619	GO:0050790	0.825081	Regulation of catalytic activity (1)	4.0	1.0	0.598054
476	GO:0048714	0.112165	Positive regulation of oligodendrocyte differentiation (1)	0.0	1.0	0.593772
363	GO:0051494	0.232679	Negative regulation of cytoskeleton organization (1)	2.0	1.0	0.593448
652	GO:0042180	0.090402	Cellular ketone metabolic process (1)	3.0	1.0	0.590857
423	GO:1902533	0.530199	Positive regulation of intracellular signal transduction (1)	2.0	1.0	0.581066
319	GO:0006909	0.217477	Phagocytosis (1)	2.0	1.0	0.578885
353	GO:0006954	0.482633	Inflammatory response (1)	3.0	1.0	0.578336
406	GO:0048041	0.319689	Focal adhesion assembly (1)	1.0	1.0	0.577606
585	GO:0048589	0.599054	Developmental growth (1)	4.0	1.0	0.575879
461	GO:0050804	0.367884	Modulation of chemical synaptic transmission (1)	3.0	1.0	0.568933
711	GO:0019752	0.316625	Carboxylic acid metabolic process (1)	4.0	1.0	0.563481
629	GO:0051174	0.783163	Regulation of phosphorus metabolic process (1)	6.0	1.0	0.558257
82	GO:0032743	0.079738	Positive regulation of interleukin-2 production (1)	0.0	1.0	0.545266
510	GO:0042063	0.408279	Gliogenesis (1)	3.0	1.0	0.539129
730	GO:0031175	0.631148	Neuron projection development (1)	4.0	1.0	0.537147
741	GO:0016477	0.682158	Cell migration (1)	4.0	1.0	0.536651
663	GO:0050821	0.165950	Protein stabilization (1)	0.0	1.0	0.535214
343	GO:1902166	0.145254	Negative regulation of intrinsic apoptotic signaling pathway in response to dna damage by p53 class mediator (1)	0.0	1.0	0.525494
213	GO:0006396	0.268052	Rna processing (1)	4.0	1.0	0.523646
563	GO:1900272	0.063979	Negative regulation of long-term synaptic potentiation (1)	0.0	1.0	0.517858
36	GO:0000723	0.137533	Telomere maintenance (1)	1.0	1.0	0.515446
524	GO:0007519	0.230417	Skeletal muscle tissue development (1)	2.0	1.0	0.511692
93	GO:0001843	0.082584	Neural tube closure (1)	1.0	1.0	0.491845
226	GO:0035304	0.232643	Regulation of protein dephosphorylation (1)	2.0	1.0	0.490892
684	GO:0051770	0.158964	Positive regulation of nitric-oxide synthase biosynthetic process (1)	0.0	1.0	0.483868
583	GO:0032967	0.182852	Positive regulation of collagen biosynthetic process (1)	0.0	1.0	0.478922
641	GO:0071417	0.494543	Cellular response to organonitrogen compound (1)	3.0	1.0	0.475108
788	GO:0009410	0.407937	Response to xenobiotic stimulus (1)	2.0	1.0	0.474799
412	GO:0009966	0.816584	Regulation of signal transduction (1)	5.0	1.0	0.474348
735	GO:0046718	0.151222	Viral entry into host cell (1)	1.0	1.0	0.472175
266	GO:0030163	0.372430	Protein catabolic process (1)	4.0	1.0	0.453053
196	GO:0006357	0.230696	Regulation of transcription by rna polymerase ii (1)	3.0	1.0	0.447389
840	GO:0043154	0.084113	Negative regulation of cysteine-type endopeptidase activity involved in apoptotic process (1)	1.0	1.0	0.427212
299	GO:0030705	0.133167	Cytoskeleton-dependent intracellular transport (1)	3.0	1.0	0.424567
433	GO:0097191	0.302625	Extrinsic apoptotic signaling pathway (1)	3.0	1.0	0.420731
610	GO:0031333	0.191284	Negative regulation of protein-containing complex assembly (1)	2.0	1.0	0.417629
501	GO:0007507	0.480118	Heart development (1)	4.0	1.0	0.417365
901	GO:0042110	0.432222	T cell activation (1)	4.0	1.0	0.413843
260	GO:0006807	0.931522	Nitrogen compound metabolic process (1)	7.0	1.0	0.413085
785	GO:0009266	0.178944	Response to temperature stimulus (1)	2.0	1.0	0.412491
358	GO:0007005	0.427023	Mitochondrion organization (1)	3.0	1.0	0.412213
377	GO:0031032	0.257340	Actomyosin structure organization (1)	2.0	1.0	0.410068
484	GO:0007399	0.731066	Nervous system development (1)	6.0	1.0	0.409544
136	GO:0002376	0.760395	Immune system process (1)	6.0	1.0	0.409057
211	GO:0031507	0.200984	Heterochromatin assembly (1)	1.0	1.0	0.406540
20	GO:0070507	0.234661	Regulation of microtubule cytoskeleton organization (1)	2.0	1.0	0.406533
356	GO:0006996	0.787638	Organelle organization (1)	5.0	1.0	0.400534
376	GO:0007015	0.344878	Actin filament organization (1)	3.0	1.0	0.399824
173	GO:0003300	0.147997	Cardiac muscle hypertrophy (1)	2.0	1.0	0.399424
620	GO:0051098	0.363823	Regulation of binding (1)	3.0	1.0	0.394294
922	GO:0036324	0.117627	Vascular endothelial growth factor receptor-2 signaling pathway (1)	0.0	1.0	0.392320
487	GO:0030325	0.087339	Adrenal gland development (1)	0.0	1.0	0.389651
781	GO:0008625	0.179216	Extrinsic apoptotic signaling pathway via death domain receptors (1)	1.0	1.0	0.375455
608	GO:0043114	0.067682	Regulation of vascular permeability (1)	1.0	1.0	0.368329
103	GO:0042531	0.243583	Positive regulation of tyrosine phosphorylation of stat protein (1)	0.0	1.0	0.365635
102	GO:0050731	0.126350	Positive regulation of peptidyl-tyrosine phosphorylation (1)	2.0	1.0	0.364186
504	GO:0048709	0.176248	Oligodendrocyte differentiation (1)	2.0	1.0	0.355145
324	GO:0016241	0.118988	Regulation of macroautophagy (1)	2.0	1.0	0.349328
218	GO:0006468	0.771378	Protein phosphorylation (1)	5.0	1.0	0.348022
171	GO:0003014	0.201637	Renal system process (1)	2.0	1.0	0.341557
644	GO:0071230	0.284292	Cellular response to amino acid stimulus (1)	1.0	1.0	0.332289
321	GO:0010507	0.205494	Negative regulation of autophagy (1)	1.0	1.0	0.332037
533	GO:0030168	0.219923	Platelet activation (1)	2.0	1.0	0.322598
546	GO:0008104	0.599923	Protein localization (1)	5.0	1.0	0.318133
362	GO:0033043	0.644550	Regulation of organelle organization (1)	4.0	1.0	0.315090
851	GO:0070933	0.058559	Histone h4 deacetylation (1)	0.0	1.0	0.313671
460	GO:0023061	0.159325	Signal release (1)	4.0	1.0	0.312808
438	GO:0007179	0.169016	Transforming growth factor beta receptor signaling pathway (1)	1.0	1.0	0.304505
300	GO:0032386	0.384834	Regulation of intracellular transport (1)	2.0	1.0	0.296704
920	GO:0036092	0.063107	Phosphatidylinositol-3-phosphate biosynthetic process (1)	0.0	1.0	0.293434
505	GO:0007283	0.290337	Spermatogenesis (1)	2.0	1.0	0.287750
357	GO:0006997	0.062583	Nucleus organization (1)	2.0	1.0	0.284535
748	GO:0009056	0.627534	Catabolic process (1)	5.0	1.0	0.276960
48	GO:0001525	0.386728	Angiogenesis (1)	2.0	1.0	0.264850
541	GO:0008542	0.131766	Visual learning (1)	0.0	1.0	0.264386
98	GO:0001932	0.669289	Regulation of protein phosphorylation (1)	4.0	1.0	0.263137
734	GO:0051702	0.152779	Biological process involved in interaction with symbiont (1)	2.0	1.0	0.263093
243	GO:0006606	0.250144	Protein import into nucleus (1)	1.0	1.0	0.261493
513	GO:0030900	0.289030	Forebrain development (1)	3.0	1.0	0.257354
673	GO:0043392	0.109472	Negative regulation of dna binding (1)	1.0	1.0	0.255228
346	GO:0006936	0.187431	Muscle contraction (1)	3.0	1.0	0.250863
552	GO:0033365	0.343027	Protein localization to organelle (1)	3.0	1.0	0.239223
9	GO:0043408	0.476159	Regulation of mapk cascade (1)	2.0	1.0	0.238056
887	GO:0034504	0.294393	Protein localization to nucleus (1)	2.0	1.0	0.236099
598	GO:0043254	0.240098	Regulation of protein-containing complex assembly (1)	3.0	1.0	0.234151
280	GO:0006810	0.773180	Transport (1)	7.0	1.0	0.229528
267	GO:0045732	0.069485	Positive regulation of protein catabolic process (1)	2.0	1.0	0.220326
668	GO:0010976	0.084952	Positive regulation of neuron projection development (1)	1.0	1.0	0.216502
212	GO:0051090	0.131395	Regulation of dna-binding transcription factor activity (1)	2.0	1.0	0.215454
799	GO:0009743	0.121060	Response to carbohydrate (1)	2.0	1.0	0.214795
675	GO:0071277	0.074147	Cellular response to calcium ion (1)	0.0	1.0	0.211553
495	GO:0060976	0.094845	Coronary vasculature development (1)	1.0	1.0	0.210353
803	GO:0042475	0.125550	Odontogenesis of dentin-containing tooth (1)	2.0	1.0	0.208932
671	GO:0032092	0.120001	Positive regulation of protein binding (1)	1.0	1.0	0.204806
772	GO:0060485	0.320964	Mesenchyme development (1)	3.0	1.0	0.203758
121	GO:0090050	0.180206	Positive regulation of cell migration involved in sprouting angiogenesis (1)	0.0	1.0	0.202697
801	GO:0033143	0.078487	Regulation of intracellular steroid hormone receptor signaling pathway (1)	1.0	1.0	0.199503
870	GO:0070527	0.179383	Platelet aggregation (1)	1.0	1.0	0.197119
314	GO:0070588	0.238228	Calcium ion transmembrane transport (1)	4.0	1.0	0.196919
656	GO:0030154	0.829241	Cell differentiation (1)	6.0	1.0	0.193962
645	GO:0071300	0.128940	Cellular response to retinoic acid (1)	0.0	1.0	0.193772
897	GO:0035767	0.138830	Endothelial cell chemotaxis (1)	1.0	1.0	0.192330
332	GO:0097190	0.410188	Apoptotic signaling pathway (1)	4.0	1.0	0.189603
643	GO:0071222	0.143456	Cellular response to lipopolysaccharide (1)	2.0	1.0	0.189188
898	GO:0035924	0.211788	Cellular response to vascular endothelial growth factor stimulus (1)	2.0	1.0	0.184593
459	GO:0007267	0.506882	Cell-cell signaling (1)	5.0	1.0	0.184371
323	GO:0016236	0.245469	Macroautophagy (1)	3.0	1.0	0.183750
317	GO:0006897	0.277768	Endocytosis (1)	3.0	1.0	0.178141
244	GO:0042307	0.225164	Positive regulation of protein import into nucleus (1)	0.0	1.0	0.177873
728	GO:0030032	0.140303	Lamellipodium assembly (1)	1.0	1.0	0.163285
640	GO:0071310	0.661841	Cellular response to organic substance (1)	4.0	1.0	0.156044
686	GO:0097009	0.055448	Energy homeostasis (1)	0.0	1.0	0.155920
692	GO:0010595	0.235403	Positive regulation of endothelial cell migration (1)	2.0	1.0	0.154755
309	GO:0034765	0.277608	Regulation of ion transmembrane transport (1)	4.0	1.0	0.153881
770	GO:0009887	0.516411	Animal organ morphogenesis (1)	4.0	1.0	0.152678
209	GO:0006338	0.181855	Chromatin remodeling (1)	2.0	1.0	0.147943
547	GO:0032880	0.479479	Regulation of protein localization (1)	4.0	1.0	0.144928
918	GO:0046854	0.054745	Phosphatidylinositol phosphate biosynthetic process (1)	1.0	1.0	0.142413
329	GO:0043066	0.610305	Negative regulation of apoptotic process (1)	4.0	1.0	0.132954
824	GO:0071363	0.407544	Cellular response to growth factor stimulus (1)	3.0	1.0	0.122808
603	GO:0061045	0.068278	Negative regulation of wound healing (1)	2.0	1.0	0.122775
225	GO:0006470	0.305848	Protein dephosphorylation (1)	3.0	1.0	0.111956
388	GO:0051726	0.483775	Regulation of cell cycle (1)	5.0	1.0	0.109432
516	GO:0007423	0.372363	Sensory organ development (1)	3.0	1.0	0.106514
261	GO:0051171	0.836045	Regulation of nitrogen compound metabolic process (1)	6.0	1.0	0.100916
375	GO:0051496	0.076120	Positive regulation of stress fiber assembly (1)	0.0	1.0	0.097110
758	GO:0031099	0.247922	Regeneration (1)	2.0	1.0	0.096133
55	GO:0001649	0.136472	Osteoblast differentiation (1)	1.0	1.0	0.091104
227	GO:0032516	0.155024	Positive regulation of phosphoprotein phosphatase activity (1)	0.0	1.0	0.090968
191	GO:0045944	0.420524	Positive regulation of transcription by rna polymerase ii (1)	2.0	1.0	0.084844
283	GO:0051049	0.611523	Regulation of transport (1)	5.0	1.0	0.084359
739	GO:1902903	0.245529	Regulation of supramolecular fiber organization (1)	3.0	1.0	0.083258
569	GO:0030307	0.190101	Positive regulation of cell growth (1)	2.0	1.0	0.078819
679	GO:0042310	0.060677	Vasoconstriction (1)	1.0	1.0	0.075349
405	GO:0007159	0.162103	Leukocyte cell-cell adhesion (1)	3.0	1.0	0.074992
566	GO:0032879	0.660318	Regulation of localization (1)	6.0	1.0	0.074219
568	GO:0008284	0.513916	Positive regulation of cell population proliferation (1)	2.0	1.0	0.073069
561	GO:0048511	0.251652	Rhythmic process (1)	3.0	1.0	0.067632
702	GO:0048146	0.179210	Positive regulation of fibroblast proliferation (1)	0.0	1.0	0.067004
403	GO:0033628	0.059919	Regulation of cell adhesion mediated by integrin (1)	1.0	1.0	0.061975
885	GO:1900180	0.205300	Regulation of protein localization to nucleus (1)	1.0	1.0	0.060202
228	GO:0006508	0.347532	Proteolysis (1)	4.0	1.0	0.056727
560	GO:0043473	0.188137	Pigmentation (1)	2.0	1.0	0.036612
777	GO:0050680	0.103322	Negative regulation of epithelial cell proliferation (1)	2.0	1.0	0.036383
751	GO:0046034	0.094236	Atp metabolic process (1)	2.0	1.0	0.034832
591	GO:0010941	0.705559	Regulation of cell death (1)	5.0	1.0	0.026616
818	GO:0010243	0.557617	Response to organonitrogen compound (1)	4.0	1.0	0.022040
724	GO:0036473	0.154959	Cell death in response to oxidative stress (1)	2.0	1.0	0.021429
153	GO:0050776	0.424435	Regulation of immune response (1)	4.0	1.0	0.011047
521	GO:0035051	0.187551	Cardiocyte differentiation (1)	2.0	1.0	0.003905
194	GO:0006355	0.544373	Regulation of transcription, dna-templated (1)	4.0	1.0	0.003607
622	GO:0043086	0.212387	Negative regulation of catalytic activity (1)	3.0	1.0	-0.003920
494	GO:0060840	0.094489	Artery development (1)	2.0	1.0	-0.013518
936	GO:0051000	0.059868	Positive regulation of nitric-oxide synthase activity (1)	0.0	1.0	-0.017649
382	GO:0030041	0.093571	Actin filament polymerization (1)	2.0	1.0	-0.024295
712	GO:0033002	0.280632	Muscle cell proliferation (1)	2.0	1.0	-0.031117
750	GO:0044281	0.305872	Small molecule metabolic process (1)	5.0	1.0	-0.053702
257	GO:0046488	0.135113	Phosphatidylinositol metabolic process (1)	2.0	1.0	-0.069795
731	GO:0031529	0.036028	Ruffle organization (1)	1.0	1.0	-0.085835
469	GO:0060173	0.072132	Limb development (1)	1.0	1.0	-0.088184
296	GO:0015031	0.292221	Protein transport (1)	4.0	1.0	-0.098692
927	GO:0042632	0.034870	Cholesterol homeostasis (1)	0.0	1.0	-0.119705
78	GO:0032760	0.100402	Positive regulation of tumor necrosis factor production (1)	0.0	1.0	-0.132748
856	GO:0019722	0.034146	Calcium-mediated signaling (1)	2.0	1.0	-0.141431
288	GO:0032940	0.217398	Secretion by cell (1)	5.0	1.0	-0.147194
705	GO:0051353	0.082787	Positive regulation of oxidoreductase activity (1)	1.0	1.0	-0.158575
176	GO:0044262	0.129234	Cellular carbohydrate metabolic process (1)	3.0	1.0	-0.190099
180	GO:0019318	0.046251	Hexose metabolic process (1)	2.0	1.0	-0.211363
440	GO:0030512	0.045444	Negative regulation of transforming growth factor beta receptor signaling pathway (1)	0.0	1.0	-0.229806
331	GO:0071887	0.072964	Leukocyte apoptotic process (1)	2.0	1.0	-0.295526
823	GO:0045471	0.068117	Response to ethanol (1)	1.0	1.0	-0.639920
232	GO:0010951	0.025246	Negative regulation of endopeptidase activity (1)	2.0	1.0	-0.917276

names2 = list(probabilities_mod.loc[probabilities_mod["predictions"] ==1].loc[probabilities_mod["layer_number"] <=7].sort_values(by=["delta_logits"], ascending=False)["Name"].head(30))
terms2 = list(probabilities_mod.loc[probabilities_mod["predictions"] ==1].loc[probabilities_mod["layer_number"] <=7].sort_values(by=["delta_logits"], ascending=False)["GO_term"].head(30))
logits2 = list(probabilities_mod.loc[probabilities_mod["predictions"] ==1].loc[probabilities_mod["layer_number"] <=7].sort_values(by=["delta_logits"], ascending=False)["delta_logits"].head(30))

names2 = [x[:-4] for x in names2] 

for i in range(0,len(names2)):
    print(terms2[i],names2[i],logits2[i])

GO:0031047 Gene silencing by rna 2.192457619336144
GO:0031648 Protein destabilization 2.092833916210919
GO:0071900 Regulation of protein serine/threonine kinase activity 1.944569179670069
GO:0000423 Mitophagy 1.8800065969407627
GO:0048266 Behavioral response to pain 1.8570307139212263
GO:0090630 Activation of gtpase activity 1.793943480641404
GO:0045727 Positive regulation of translation 1.7460704310285706
GO:0018108 Peptidyl-tyrosine phosphorylation 1.6728257190053135
GO:0043244 Regulation of protein-containing complex disassembly 1.6460980615310405
GO:0006612 Protein targeting to membrane 1.6268405228374492
GO:0006469 Negative regulation of protein kinase activity 1.5937943848967007
GO:0034976 Response to endoplasmic reticulum stress 1.575980420814227
GO:0071353 Cellular response to interleukin-4 1.5752555355925209
GO:0033554 Cellular response to stress 1.573975479674923
GO:0033993 Response to lipid 1.5515734212063519
GO:0001817 Regulation of cytokine production 1.5347154822720621
GO:0007026 Negative regulation of microtubule depolymerization 1.5337813437727923
GO:0007565 Female pregnancy 1.4788810435976616
GO:0046777 Protein autophosphorylation 1.453821209026271
GO:0060179 Male mating behavior 1.4409006464912832
GO:0000422 Autophagy of mitochondrion 1.4098807478143418
GO:0030216 Keratinocyte differentiation 1.406529668352229
GO:0048812 Neuron projection morphogenesis 1.3850039160074457
GO:0001553 Luteinization 1.3733255324441331
GO:0002718 Regulation of cytokine production involved in immune response 1.3728274508963876
GO:0042060 Wound healing 1.325910525701464
GO:0060632 Regulation of microtubule-based movement 1.3061039503079361
GO:0065003 Protein-containing complex assembly 1.304383769510548
GO:0060020 Bergmann glial cell differentiation 1.2886961413918279
GO:1902459 Positive regulation of stem cell population maintenance 1.2787216247479065

# import libraries
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
%matplotlib inline

# set font
plt.rcParams['font.family'] = 'sans-serif'
plt.rcParams['font.sans-serif'] = 'Roboto'

# set the style of the axes and the text color
plt.rcParams['axes.edgecolor']='#333F4B'
plt.rcParams['axes.linewidth']=0.8
plt.rcParams['xtick.color']='#333F4B'
plt.rcParams['ytick.color']='#333F4B'
plt.rcParams['text.color']='#333F4B'


# create some fake data
percentages = pd.Series(logits2, 
                        index=names2)
df = pd.DataFrame({'percentage' : percentages})
df = df.sort_values(by='percentage')

# we first need a numeric placeholder for the y axis
my_range=list(range(1,len(df.index)+1))

fig, ax = plt.subplots(figsize=(4,17))

# create for each expense type an horizontal line that starts at x = 0 with the length 
# represented by the specific expense percentage value.
plt.hlines(y=my_range, xmin=0, xmax=df['percentage'], color='#208EA3', alpha=0.2, linewidth=14)

# create for each expense type a dot at the level of the expense percentage value
plt.plot(df['percentage'], my_range, "o", markersize=14, color='#208EA3', alpha=0.8)

# set labels
ax.set_xlabel(' Δlogit', fontsize=25, fontweight='black', color = '#36382E')
ax.set_ylabel('')
ax.set_facecolor(color="white")
ax.set_alpha(1)

# set axis
ax.tick_params(axis='both', which='major', labelsize=30)
plt.yticks(my_range, df.index)

# add an horizonal label for the y axis 
fig.text(-0.58, 0.862, 'MoA (GO terms)', fontsize=27, fontweight='black', color = '#36382E')
fig.text(0.2, 0.9, selected_drug_u_name.capitalize(), fontsize=30, fontweight='black', color = '#36382E')


# change the style of the axis spines
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)

ax.spines['left'].set_bounds((1, len(my_range)))
ax.set_xlim(0,max(logits2)+0.1)

ax.spines['left'].set_position(('outward', 8))
ax.spines['bottom'].set_position(('outward', 5))

plt.savefig(resultsdir+selected_drug_u_name+'_top_terms.png', dpi=300, bbox_inches='tight')

For known drug…

display(combobox)

selected_drug_name = combobox.result

# LOS LOGITS DE TEST!!
train_drug_logs = pd.DataFrame(platt_matrix.loc[:,selected_drug_name]).reset_index()
train_drug_logs.columns  = ["GO_term","probability"]
train_drug_logs = train_drug_logs.merge(real_go_info_svm, on="GO_term")

train_drug_logs.loc[train_drug_logs["layer_number"] <=3].sort_values(by=["probability"], ascending=False).head(30)

	GO_term	probability	Name	layer_number
423	GO:1902533	0.825532	Positive regulation of intracellular signal transduction (1)	2.0
99	GO:0001934	0.823688	Positive regulation of protein phosphorylation (1)	3.0
633	GO:0051301	0.817491	Cell division (1)	2.0
224	GO:0046777	0.780375	Protein autophosphorylation (1)	1.0
8	GO:0000165	0.778813	Mapk cascade (1)	3.0
624	GO:0010628	0.741437	Positive regulation of gene expression (1)	3.0
253	GO:0043552	0.735601	Positive regulation of phosphatidylinositol 3-kinase activity (1)	0.0
437	GO:0007169	0.646597	Transmembrane receptor protein tyrosine kinase signaling pathway (1)	3.0
653	GO:0072593	0.631785	Reactive oxygen species metabolic process (1)	3.0
894	GO:0048017	0.609803	Inositol lipid-mediated signaling (1)	1.0
578	GO:2000379	0.603184	Positive regulation of reactive oxygen species metabolic process (1)	1.0
24	GO:0007346	0.596523	Regulation of mitotic cell cycle (1)	3.0
573	GO:0010629	0.592396	Negative regulation of gene expression (1)	3.0
908	GO:0051899	0.591286	Membrane depolarization (1)	2.0
906	GO:0043549	0.586633	Regulation of kinase activity (1)	3.0
105	GO:0045860	0.585544	Positive regulation of protein kinase activity (1)	2.0
12	GO:0070374	0.584467	Positive regulation of erk1 and erk2 cascade (1)	0.0
74	GO:0001817	0.527795	Regulation of cytokine production (1)	3.0
44	GO:0048812	0.526118	Neuron projection morphogenesis (1)	3.0
853	GO:0038083	0.500000	Peptidyl-tyrosine autophosphorylation (1)	0.0
223	GO:0018108	0.493038	Peptidyl-tyrosine phosphorylation (1)	3.0
9	GO:0043408	0.472479	Regulation of mapk cascade (1)	2.0
570	GO:0045597	0.464440	Positive regulation of cell differentiation (1)	3.0
333	GO:1904019	0.457451	Epithelial cell apoptotic process (1)	1.0
702	GO:0048146	0.440487	Positive regulation of fibroblast proliferation (1)	0.0
80	GO:0010575	0.438910	Positive regulation of vascular endothelial growth factor production (1)	0.0
106	GO:0071900	0.437003	Regulation of protein serine/threonine kinase activity (1)	2.0
141	GO:0050900	0.435245	Leukocyte migration (1)	3.0
10	GO:0051403	0.429898	Stress-activated mapk cascade (1)	2.0
11	GO:0043406	0.426305	Positive regulation of map kinase activity (1)	1.0

# # For known drugs
len((set(train_drug_logs.loc[train_drug_logs["layer_number"] <=3].sort_values(by=["probability"], ascending=False).head(30)["GO_term"])).intersection(set(pd.DataFrame(compounds_GOterms_matches[selected_drug_name])[1])))

30

ax = sns.boxplot(x=slim_matrix_single_neuron.loc[train_drug_logs["GO_term"],selected_drug_name], y=train_drug_logs.set_index("GO_term")["probability"], data=plot,showfliers=True )

# same as before
sum_annotations = slim_matrix_single_neuron.T.sum()/slim_matrix_single_neuron.shape[1]
logits_apriori= np.log(sum_annotations/(1-sum_annotations))

logits_apost= np.log(train_drug_logs["probability"]/(1-train_drug_logs["probability"]))
delta_logits = logits_apost.to_numpy()-logits_apriori.to_numpy()
delta_logits_df = pd.DataFrame(delta_logits)
delta_logits_df.columns = ["delta_logits"]
train_drug_mod = train_drug_logs.merge(delta_logits_df, left_index=True,right_index=True)

train_drug_mod.loc[train_drug_mod["layer_number"] <=3].sort_values(by=["delta_logits"], ascending=False).head(30)

	GO_term	probability	Name	layer_number	delta_logits
578	GO:2000379	0.603184	Positive regulation of reactive oxygen species metabolic process (1)	1.0	2.770126
253	GO:0043552	0.735601	Positive regulation of phosphatidylinositol 3-kinase activity (1)	0.0	2.707570
80	GO:0010575	0.438910	Positive regulation of vascular endothelial growth factor production (1)	0.0	2.282492
633	GO:0051301	0.817491	Cell division (1)	2.0	2.245231
224	GO:0046777	0.780375	Protein autophosphorylation (1)	1.0	2.053782
423	GO:1902533	0.825532	Positive regulation of intracellular signal transduction (1)	2.0	2.014408
458	GO:0035025	0.374269	Positive regulation of rho protein signal transduction (1)	0.0	1.952270
848	GO:0071670	0.345148	Smooth muscle cell chemotaxis (1)	0.0	1.887644
348	GO:0006939	0.412178	Smooth muscle contraction (1)	2.0	1.842256
350	GO:0045987	0.348868	Positive regulation of smooth muscle contraction (1)	1.0	1.783402
908	GO:0051899	0.591286	Membrane depolarization (1)	2.0	1.675960
653	GO:0072593	0.631785	Reactive oxygen species metabolic process (1)	3.0	1.650121
115	GO:0060312	0.275354	Regulation of blood vessel remodeling (1)	0.0	1.625762
926	GO:0060020	0.369360	Bergmann glial cell differentiation (1)	0.0	1.614859
923	GO:0048170	0.295742	Positive regulation of long-term neuronal synaptic plasticity (1)	0.0	1.598558
99	GO:0001934	0.823688	Positive regulation of protein phosphorylation (1)	3.0	1.593723
853	GO:0038083	0.500000	Peptidyl-tyrosine autophosphorylation (1)	0.0	1.588712
713	GO:0035726	0.210551	Common myeloid progenitor cell proliferation (1)	0.0	1.577983
445	GO:0048008	0.414654	Platelet-derived growth factor receptor signaling pathway (1)	1.0	1.552362
857	GO:0035584	0.298388	Calcium-mediated signaling using intracellular calcium source (1)	0.0	1.496390
333	GO:1904019	0.457451	Epithelial cell apoptotic process (1)	1.0	1.481165
933	GO:0051150	0.337253	Regulation of smooth muscle cell differentiation (1)	1.0	1.474264
352	GO:0014827	0.254529	Intestine smooth muscle contraction (1)	0.0	1.453480
814	GO:0090037	0.235572	Positive regulation of protein kinase c signaling (1)	0.0	1.416277
894	GO:0048017	0.609803	Inositol lipid-mediated signaling (1)	1.0	1.399588
506	GO:0007286	0.240113	Spermatid development (1)	1.0	1.376021
742	GO:0035733	0.239304	Hepatic stellate cell activation (1)	0.0	1.371582
10	GO:0051403	0.429898	Stress-activated mapk cascade (1)	2.0	1.369506
702	GO:0048146	0.440487	Positive regulation of fibroblast proliferation (1)	0.0	1.349525
782	GO:1902042	0.289337	Negative regulation of extrinsic apoptotic signaling pathway via death domain receptors (1)	0.0	1.347889

ax = sns.boxplot(x=slim_matrix_single_neuron.loc[train_drug_mod["GO_term"],selected_drug_name], y=train_drug_mod.set_index("GO_term")["delta_logits"], data=plot,showfliers=True)

SVM GO TERM 2D representation

from sklearn.manifold import TSNE
import plotly.express as px

Choose go to study…

display(combobox_go)

selected_goterm = combobox_go.result

real_go_info[real_go_info["GO_term"]==selected_goterm+"_1"]

	GO_term	Name	layer_number
4338	GO:0071353_1	Cellular response to interleukin-4 (1)	1.0

list_nodes = []
for i in range(1,7):
    list_nodes.append(selected_goterm+"_"+str(i))

score = attribution_data_annotated.loc[list_nodes].T
score_mod = score.divide(score.std()).fillna(0) 
annotations  =slim_matrix_single_neuron.loc[selected_goterm,]
y_predicted = models_svm[selected_goterm].predict(score_mod.astype(float))

Plot SVM

View statistics of GOterm

“Perfect” model (with train data)

auc = metrics.roc_auc_score(annotations, models_svm[selected_goterm].decision_function(score_mod.astype(float)))
cnf_matrix = metrics.confusion_matrix(annotations,y_predicted)
print(cnf_matrix)

print("Accuracy:",metrics.accuracy_score(annotations, y_predicted))
print("Precision:",metrics.precision_score(annotations,y_predicted)) # TP / (TP+FP)
print("Recall:",metrics.recall_score(annotations, y_predicted)) #TP / (TP+FN)
print("AUC with score:",auc) 

[[206   6]
 [  2  16]]
Accuracy: 0.9652173913043478
Precision: 0.7272727272727273
Recall: 0.8888888888888888
AUC with score: 0.9855870020964361

TN - FP

FN - TP

En mi opinion interesa mucho el precision, prefiero que haya menos FP no??

Test statistics…

auc = metrics.roc_auc_score(slim_matrix_single_neuron.loc[selected_goterm],  platt_matrix.loc[selected_goterm])
cnf_matrix = metrics.confusion_matrix(slim_matrix_single_neuron.loc[selected_goterm], preds_svm_matrix.loc[selected_goterm])
print(cnf_matrix)

print("Accuracy:",metrics.accuracy_score(slim_matrix_single_neuron.loc[selected_goterm], preds_svm_matrix.loc[selected_goterm]))
print("Precision:",metrics.precision_score(slim_matrix_single_neuron.loc[selected_goterm], preds_svm_matrix.loc[selected_goterm]))
print("Recall:",metrics.recall_score(slim_matrix_single_neuron.loc[selected_goterm], preds_svm_matrix.loc[selected_goterm])) #TP / (TP+FN)
print("AUC with score:",auc) #TP / (TP+FN)

[[203   9]
 [  4  14]]
Accuracy: 0.9434782608695652
Precision: 0.6086956521739131
Recall: 0.7777777777777778
AUC with score: 0.9095911949685536

import colorlover as cl
matrix = metrics.confusion_matrix(annotations,y_predicted)
tn, fp, fn, tp = matrix.ravel()

values = [tp, fn, fp, tn]
label_text = ["True Positive", "False Negative", "False Positive", "True Negative"]
labels = ["<b>TP</b>", "<b>FN</b>", "<b>FP</b>", "<b>TN</b>"]
blue = cl.flipper()["seq"]["9"]["Blues"]
red = cl.flipper()["seq"]["9"]["Reds"]
colors = ["#ff3700","#FFA0A0", "#CCE9FF",  "#0b8bff"]
trace0 = go.Pie(
    labels=label_text,
    values=values,
    hoverinfo="label+value+percent",
    textinfo="text+value",
    text=labels,
    sort=False,
    marker=dict(colors=colors),
    insidetextfont={"color": "#36382E"},
    rotation=90,
)

layout = go.Layout(
    title=dict(text="Confusion Matrix",
              x=0.3,
              y=0.8,
              font=dict(size=14),
              xanchor='center',
              yanchor='top'),
    #margin=dict(l=50, r=50, t=100, b=10),
    legend=dict(font={"color": "#36382E"}, orientation="h",x=0.1, y=-0.03),
#    plot_bgcolor="#282b38",
#    paper_bgcolor="#282b38",
    font=dict(family='Roboto',color= "#36382E"),
)

data = [trace0]
figure = go.Figure(data=data, layout=layout)
figure

y_test=annotations
decision_test=y_predicted
fpr, tpr, threshold = metrics.roc_curve(y_test, decision_test)

# AUC Score
auc_score = metrics.roc_auc_score(y_true=y_test, y_score=decision_test)

trace0 = go.Scatter(
    x=fpr, y=tpr, mode="lines", name="Test Data", marker={"color": "#ff3700"}
)

layout = go.Layout(
    title=dict(text=f"ROC Curve (AUC = {auc_score:.3f})",
            x=0.6,
            y=0.5,
            font=dict(size=20)
              ),
    xaxis=dict(title="False Positive Rate", gridcolor="white"),
    yaxis=dict(title="True Positive Rate", gridcolor="white"),
    legend=dict(x=0, y=1.05, orientation="h"),
    margin=dict(l=100, r=10, t=25, b=40),
#    plot_bgcolor="#282b38",
#    paper_bgcolor="#282b38",
    font=dict(family='Roboto',color= "#36382E"),
)

data = [trace0]
figure = go.Figure(data=data, layout=layout)
figure

Plot SVM with unknown labels

Voronoi Tessellation

What is a Voronoi Tessellation? Given a set P := {p1, …, pn} of sites, a Voronoi Tessellation is a subdivision of the space into n cells, one for each site in P, with the property that a point q lies in the cell corresponding to a site pi iff d(pi, q) < d(pj, q) for i distinct from j. The segments in a Voronoi Tessellation correspond to all points in the plane equidistant to the two nearest sites. Voronoi Tessellations have applications in computer science.

https://stackoverflow.com/questions/61225052/svm-plot-decision-surface-when-working-with-more-than-2-features

tsne = TSNE(n_components=2, verbose=0,
           init="pca",
            perplexity=30,
            random_state=123
           )
z = tsne.fit_transform(score_mod.astype(float)) 

C:\Users\ksada\Anaconda3\envs\SparseGO\lib\site-packages\sklearn\manifold\_t_sne.py:790: FutureWarning:

The default learning rate in TSNE will change from 200.0 to 'auto' in 1.2.

C:\Users\ksada\Anaconda3\envs\SparseGO\lib\site-packages\sklearn\manifold\_t_sne.py:982: FutureWarning:

The PCA initialization in TSNE will change to have the standard deviation of PC1 equal to 1e-4 in 1.2. This will ensure better convergence.

list_nodes = list(models_svm[selected_goterm].feature_names_in_) # Extract the feature names from the model (those are the attributions we need)
score_unknown = attribution_data_all.loc[list_nodes,unknown].T
score_unknown_mod = score_unknown.divide(score.std()).fillna(0) # normalize

y_unknown = np.full(score_unknown_mod.shape[0],2) # 2=unknown MOA
y_pred_unknown = models_svm[selected_goterm].predict(score_unknown_mod.astype(float))

# join scores and annotations from known and unknown drugs
all_score = pd.concat([score_mod,score_unknown_mod])
all_y = np.concatenate((annotations,y_unknown))  # 2=unknown MOA

Plot T-SNE SVM

from sklearn.neighbors._classification import KNeighborsClassifier
# https://github.com/plotly/dash-sample-apps/blob/main/apps/dash-svm/utils/dash_reusable_components.py
z = tsne.fit_transform(all_score.astype(float)) 
df = pd.DataFrame()
df["y"] = all_y
df["comp-1"] = z[:,0]
df["comp-2"] = z[:,1]
df["name"] =list(all_score.index)
df = df.sort_values(by=['y'])
df["y"] = df["y"].astype(str)
X,y = all_score.astype(float), all_y
y_predicted = models_svm[selected_goterm].predict(X)

resolution = 300 # 100x100 background pixels
X2d_xmin, X2d_xmax = np.min(z[:,0])-1, np.max(z[:,0])+1
X2d_ymin, X2d_ymax = np.min(z[:,1])-1, np.max(z[:,1])+1
xx, yy = np.meshgrid(np.linspace(X2d_xmin, X2d_xmax, resolution), np.linspace(X2d_ymin, X2d_ymax, resolution))

# approximate Voronoi tesselation on resolution x resolution grid using 1-NN
background_model = KNeighborsClassifier(n_neighbors=1).fit(z, y_predicted) 
voronoiBackground = background_model.predict(np.c_[xx.ravel(), yy.ravel()])
voronoiBackground = voronoiBackground.reshape((resolution, resolution))

C:\Users\ksada\Anaconda3\envs\SparseGO\lib\site-packages\sklearn\manifold\_t_sne.py:790: FutureWarning:

The default learning rate in TSNE will change from 200.0 to 'auto' in 1.2.

C:\Users\ksada\Anaconda3\envs\SparseGO\lib\site-packages\sklearn\manifold\_t_sne.py:982: FutureWarning:

The PCA initialization in TSNE will change to have the standard deviation of PC1 equal to 1e-4 in 1.2. This will ensure better convergence.

C:\Users\ksada\Anaconda3\envs\SparseGO\lib\site-packages\sklearn\neighbors\_classification.py:228: FutureWarning:

Unlike other reduction functions (e.g. `skew`, `kurtosis`), the default behavior of `mode` typically preserves the axis it acts along. In SciPy 1.11.0, this behavior will change: the default value of `keepdims` will become False, the `axis` over which the statistic is taken will be eliminated, and the value None will no longer be accepted. Set `keepdims` to True or False to avoid this warning.

go_name=real_go_info[real_go_info["GO_term"]==selected_goterm+"_1"]["Name"].values[0][:-4]
go_name

'Cellular response to interleukin-4'

bright_cscale = [[0, "#0b8bff"], [0.5, "#ff3700"],[1, "#36382E"]]
new_cscale = [[0, "#CCE9FF"], [1, "#FFA0A0"]]

trace0 = go.Contour(
        x=xx.flatten(),
        y=yy.flatten(),
        z=voronoiBackground.flatten(),
        hoverinfo="none",
        showscale=False,
        contours=dict(showlines=False),
        colorscale=new_cscale,
        opacity=0.9,
    )
    
trace1 = go.Contour(
    x=xx.flatten(),
    y=yy.flatten(),
    z=voronoiBackground.flatten(),
    showscale=False,
    hoverinfo="none",
    colorscale=new_cscale,
    line=dict(color="#ff3700"),
    )

trace2 = go.Scatter(
    x=df["comp-1"],
    y=df["comp-2"],
    mode="markers",
    text=df["name"].to_numpy(),
    marker=dict(size=7, color=df["y"].to_numpy(int),colorscale=bright_cscale),
    showlegend=False
)

legend1 = go.Scatter(
    x=[None],
    y=[None],
    mode="markers",
    name="Not annotated to<br>"+selected_goterm,
    marker=dict(size=7, color="#0b8bff",symbol='circle'),
)

legend2 = go.Scatter(
    x=[None],
    y=[None],
    mode="markers",
    name="Drug annotated to<br>"+selected_goterm,
    marker=dict(size=7, color="#ff3700",symbol='circle'),
)

legend3 = go.Scatter(
    x=[None],
    y=[None],
    mode="markers",
    name="Unknown MOA<br>annotations",
    marker=dict(size=7, color="#36382E",symbol='circle'),
)

    
layout = go.Layout(
   title=dict(text="<b>"+selected_goterm+"</b> "+go_name,
              x=0.5,
              y=0.92,
              font=dict(size=18),
              xanchor='center',
              yanchor='top'),
    xaxis=dict(ticks="", showticklabels=False, showgrid=False, zeroline=False),
    yaxis=dict(ticks="", showticklabels=False, showgrid=False, zeroline=False),
    yaxis_range=[min(yy.flatten()),max(yy.flatten())],
    xaxis_range=[min(xx.flatten()),max(xx.flatten())],
    legend=dict(x=0, y=0, orientation="h",font=dict(size=14)),
    paper_bgcolor='rgba(0,0,0,0)',
    width=600, height=800,
    font=dict(family='Roboto',color= "#36382E",size=15)
    )
data = [trace0,trace1,trace2,legend2,legend1,legend3]
figure = go.Figure(data=data,layout=layout)




figure